INDEX

Explanations

frequent mentions of introductory phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

клопе

-0.68

alate

-0.58

niques

-0.58

midt

-0.55

hava

-0.55

omla

-0.54

entration

-0.54

tivation

-0.54

ztes

-0.54

 large

-0.53

POSITIVE LOGITS

 course

1.05

course

0.80

 COURSE

0.80

awtextra

0.73

Course

0.65

 Course

0.64

 tudo

0.59

COURSE

0.59

 conseguenza

0.59

EndInit

0.56

Activations Density 0.169%

frequent mentions of introductory phrases

No Comments

No Known Activations