INDEX

Explanations

punctuation marks

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

academic citations and URLs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ſelf

-0.89

 ſch

-0.73

 ſta

-0.72

 raiſ

-0.72

 ſte

-0.72

出版年

-0.71

 neceſſ

-0.71

 deſt

-0.71

 faſt

-0.69

 houſe

-0.69

POSITIVE LOGITS

://

0.66

doi

0.39

doi

0.38

 xmlns

0.37

VersionUID

0.37

0.36

www

0.33

Ho

0.33

www

0.33

fasterxml

0.31

Activations Density 0.005%

punctuation marks

academic citations and URLs

No Comments

No Known Activations