INDEX

Explanations

punctuation marks and formatting symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 their

-0.65

ten

-0.56

see

-0.56

he

-0.53

saw

-0.51

٪

-0.50

 aventures

-0.49

 sees

-0.48

 special

-0.48

la

-0.48

POSITIVE LOGITS

tvguidetime

0.58

 يتيمه

0.56

出版年

0.55

 StringTokenizer

0.54

 armband

0.53

rawDesc

0.51

WillAppear

0.51

 AssemblyCompany

0.51

 kakao

0.50

+:+

0.49

Activations Density 0.099%

punctuation marks and formatting symbols

No Comments

No Known Activations