INDEX

Explanations

negative expressions or dismissals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

waf

-0.59

ticles

-0.58

ArgumentParser

-0.54

OGND

-0.53

 lomb

-0.52

 Bender

-0.50

هما

-0.50

Népesség

-0.49

 charbon

-0.48

 Jacinto

-0.48

POSITIVE LOGITS

not

1.19

not

0.97

NOT

0.95

Not

0.94

NOT

0.91

不

0.90

Not

0.89

 не

0.86

 không

0.79

ไม่

0.79

Activations Density 0.151%

negative expressions or dismissals

No Comments

No Known Activations