INDEX

Explanations

phrases related to community concerns and legal issues

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

 esternos

-0.82

AndEndTag

-0.77

 BorderSide

-0.70

bootstrapcdn

-0.69

fjspx

-0.66

 ModelExpression

-0.66

 LCCN

-0.65

 mergeFrom

-0.65

 étoit

-0.65

apimachinery

-0.65

POSITIVE LOGITS

 fair

0.44

もっと

0.44

制度

0.43

 legislation

0.43

 should

0.43

 unfair

0.41

anet

0.41

 propose

0.41

 streamlined

0.41

FAIR

0.41

Activations Density 0.141%

phrases related to community concerns and legal issues

No Comments

No Known Activations