INDEX

Explanations

The word "judges" appearing in various legal and judicial contexts, sometimes in lists of categories or titles, and sometimes within descriptions of court proceedings and decisions.

eleuther_acts_top20 · gemini-1.5-flash Triggered by @johnny

references to judges and the judicial system

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 alre

-0.62

 >=",

-0.60

 Signalez

-0.60

تقاوى

-0.58

برا

-0.57

참고

-0.55

 Réponses

-0.55

 vété

-0.54

ONOM

-0.54

 Fright

-0.54

POSITIVE LOGITS

avatar

0.83

 bore

0.76

 resourceCulture

0.73

 Avatar

0.70

 avatar

0.70

 judges

0.68

weilen

0.68

ador

0.67

 touchdown

0.67

bore

0.66

Activations Density 0.087%

The word "judges" appearing in various legal and judicial contexts, sometimes in lists of categories or titles, and sometimes within descriptions of court proceedings and decisions.

references to judges and the judicial system

No Comments

No Known Activations