INDEX

Explanations

phrases related to conditions and relationships in mathematical or scientific contexts

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

DebuggerNonUser

-0.74

BeginInit

-0.69

 ""],

-0.68

 Roskov

-0.67

 يتيمه

-0.67

 bParam

-0.63

 Civi

-0.62

eeq

-0.61

Tikang

-0.60

StructEnd

-0.60

POSITIVE LOGITS

 scolaires

0.80

 religieuses

0.69

 étrangères

0.67

 supérieures

0.62

 fréquent

0.62

 malade

0.61

tvguidetime

0.60

 prisonniers

0.59

 ביותר

0.58

 soldati

0.57

Activations Density 0.594%

phrases related to conditions and relationships in mathematical or scientific contexts

No Comments

No Known Activations