INDEX

Explanations

references to dressing or attire

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

dress up in

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ніципалі

-0.55

 pinulongan

-0.52

EndProject

-0.52

principalColumn

-0.48

 հղումներ

-0.47

 endforeach

-0.47

ganggu

-0.46

UTERS

-0.46

astéroïdes

-0.46

astéro

-0.45

POSITIVE LOGITS

 dressed

0.79

dressed

0.69

 DRESS

0.65

 clothed

0.64

Dress

0.64

 dressing

0.62

 dress

0.59

 Dressed

0.57

打扮

0.57

 Dress

0.57

Activations Density 0.009%

references to dressing or attire

dress up in

No Comments

No Known Activations