INDEX

Explanations

special symbols and formatting cues typical in programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

fjspx

-0.81

 ModelExpression

-0.74

 везе

-0.68

principalTable

-0.66

xodo

-0.64

bolista

-0.63

 linkovi

-0.59

 nonUne

-0.59

SourceChecksum

-0.58

AccessFile

-0.57

POSITIVE LOGITS

 AppColors

0.58

 authService

0.56

phosa

0.54

 resultCode

0.53

 propTypes

0.53

nehå

0.52

텝

0.52

mrow

0.49

\{\\

0.49

cré

0.48

Activations Density 0.020%

special symbols and formatting cues typical in programming or markup languages

No Comments

No Known Activations