INDEX

Explanations

occurrences of the word "this" and various punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

CopyWith

-0.81

}}/>

-0.76

 चीज़ों

-0.72

 GetEnumerator

-0.70

 متعلقه

-0.69

исленность

-0.69

Халык

-0.68

BuilderFactory

-0.67

queryInterface

-0.67

thâu

-0.65

POSITIVE LOGITS

 domanda

0.67

 sanitaires

0.66

 portata

0.63

 aéri

0.62

 ouvertes

0.62

 puissante

0.61

 utilizzo

0.60

 situazioni

0.60

 significato

0.59

 sencillas

0.59

Activations Density 0.015%

occurrences of the word "this" and various punctuation marks

No Comments

No Known Activations