INDEX

Explanations

words beginning with the letter 'g'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

principalColumn

-0.66

brainly

-0.64

ViewFeatures

-0.64

DoubleQuotes

-0.63

InitVars

-0.57

 mouthful

-0.49

 kaynağından

-0.48

featureID

-0.48

thenReturn

-0.48

 Baillargeon

-0.48

POSITIVE LOGITS

RenderAtEndOf

0.59

toMatchSnapshot

0.56

windowFixed

0.55

esgue

0.54

Географиясе

0.51

InputBorder

0.51

BITDA

0.50

 ModelExpression

0.49

 يتيمه

0.48

azy

0.47

Activations Density 0.263%

words beginning with the letter 'g'

No Comments

No Known Activations