INDEX

Explanations

the beginning of different segments or sections in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

OGND

-0.90

extAlignment

-0.88

 EconPapers

-0.88

 nahilalakip

-0.86

parsedMessage

-0.86

RetentionPolicy

-0.83

 AssemblyCulture

-0.81

HtmlAttribute

-0.81

 Италијани

-0.81

 ―――――

-0.78

POSITIVE LOGITS

 game

0.57

 Game

0.51

Game

0.49

 gameplay

0.48

↵

0.47

game

0.47

0.45

TD

0.44

0.43

Activations Density 0.210%

the beginning of different segments or sections in a document

No Comments

No Known Activations