INDEX

Explanations

various forms of the word "comment"

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

"Comment" or words following "comment"

np_acts-logits-general · gemini-2.0-flash

comment:

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 BorderRadius

-0.70

AlterField

-0.53

Kilder

-0.50

 objectAtIndex

-0.48

ecore

-0.47

isSuccess

-0.47

 mxArray

-0.47

createServer

-0.46

takes

-0.46

awtextra

-0.45

POSITIVE LOGITS

انيف

0.80

 COMMENTS

0.79

 Comments

0.75

Välislingid

0.73

 comments

0.72

 COMMENT

0.70

 utafitiHapana

0.69

comments

0.69

 Roskov

0.66

 يتيمه

0.64

Activations Density 0.132%

various forms of the word "comment"

"Comment" or words following "comment"

comment:

No Comments

No Known Activations