INDEX

Explanations

concepts related to identity and self-perception

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

defining meaning and roles

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

DoubleQuotes

-0.59

endphp

-0.58

脚注の使い方

-0.57

########.

-0.52

 <=",

-0.52

Diwedd

-0.51

rawDesc

-0.50

 Bioaccumulative

-0.49

 GenerationType

-0.48

 <<<<<<<<<<<<<<

-0.47

POSITIVE LOGITS

 perceptions

0.45

 percepción

0.43

 perception

0.40

 Erwartungen

0.38

 imagem

0.36

のイメージ

0.36

 realidad

0.36

 conosci

0.35

 distorted

0.35

 impressions

0.35

Activations Density 0.119%

concepts related to identity and self-perception

defining meaning and roles

No Comments

No Known Activations