INDEX

Explanations

phrases related to comments and user interactions

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

 BorderRadius

-0.95

 EdgeInsets

-0.58

 objectAtIndex

-0.57

AlterField

-0.57

ecore

-0.55

 iconLine

-0.54

__(/*!

-0.54

awtextra

-0.54

Hauptartikel

-0.52

iecie

-0.52

POSITIVE LOGITS

 Comments

0.83

 COMMENT

0.81

 COMMENTS

0.80

 comments

0.79

comments

0.78

Comments

0.72

 Comment

0.71

 comment

0.70

 commenting

0.70

 remarks

0.66

Activations Density 0.079%

phrases related to comments and user interactions

No Comments

No Known Activations