INDEX

Explanations

references to specific organizations or entities related to controversial topics

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

user interaction

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

ftagPool

-0.62

ConstraintMaker

-0.60



-0.54

 препратки

-0.52

fromCharCode

-0.51

IntoConstraints

-0.50

锈钢

-0.50

 iNdEx

-0.49

 CreateTagHelper

-0.48

 BorderSide

-0.48

POSITIVE LOGITS

Focus

0.35

 nargin

0.35

 Geraadpleegd

0.34

 âgées

0.34

 viaj

0.33

Kraj

0.33

 userEmail

0.33

 Hentet

0.32

fahr

0.32

usions

0.31

Activations Density 0.000%

references to specific organizations or entities related to controversial topics

user interaction

No Comments

No Known Activations