INDEX

Explanations

references to language codes or documentation links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

RenderAtEndOf

-1.31

webElementXpaths

-1.07

ConstraintMaker

-1.06

WithIOException

-1.01

">//

-1.00

 ModelExpression

-0.97

SourceChecksum

-0.96

 "..\..\..\

-0.92

 estekak

-0.90

)))));

-0.90

POSITIVE LOGITS

EN

0.73

en

0.72

 English

0.62

 english

0.55

 sklearn

0.54

Ru

0.53

English

0.52

ENGLISH

0.52

 inglés

0.50

 ENGLISH

0.50

Activations Density 0.064%

references to language codes or documentation links

No Comments

No Known Activations