INDEX

Explanations

titles or headings in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTS

-0.71

PerformLayout

-0.61

fäl

-0.57

amssymb

-0.56

)();

-0.53

ChildIndex

-0.52

cluir

-0.52

CopyWith

-0.51

 catalyzed

-0.48

 endfor

-0.48

POSITIVE LOGITS

0.56

tamol

0.55

cydow

0.55

atguigu

0.54

følgelig

0.47

 EconPapers

0.47

رشف

0.47

 BoxDecoration

0.46

 Deber

0.46

addContainerGap

0.46

Activations Density 0.000%

titles or headings in documents

No Comments

No Known Activations