INDEX

Explanations

references to clothing and fashion contexts

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

wearing clothes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ModelSerializer

-0.44

StackNavigator

-0.43

 JpaRepository

-0.43

principalTable

-0.42

roffen

-0.38

lyd

-0.37

 tenda

-0.37

 tents

-0.36

IntoConstraints

-0.36

ollectionView

-0.36

POSITIVE LOGITS

 wearing

0.92

 wore

0.85

 wears

0.79

Wearing

0.79

 indoss

0.77

 Wearing

0.75

 donned

0.75

 wear

0.73

 dressed

0.71

wearing

0.68

Activations Density 0.022%

references to clothing and fashion contexts

wearing clothes

No Comments

No Known Activations