INDEX

Explanations

negative sentiments and accusations against individuals, particularly in a political context

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

first person statements

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

 similarly

-0.49

 Similarly

-0.48

Similarly

-0.43

WebElementEntity

-0.41

UserScript

-0.40

 تضيفلها

-0.38

 emailAlready

-0.37

gameserver

-0.35

 españolas

-0.35

 snippetHide

-0.35

POSITIVE LOGITS

rungsseite

0.59

Lue

0.52

Grand

0.51

keith

0.51

gran

0.50

routeProvider

0.50

highway

0.50

RenderAtEndOf

0.49

!!!!!

0.49

toys

0.48

Activations Density 0.285%

negative sentiments and accusations against individuals, particularly in a political context

first person statements

No Comments

No Known Activations