INDEX

Explanations

instances of user interaction with comments or posts

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

"comment" or "comments"

np_acts-logits-general · gemini-2.0-flash

user comments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.84

 EdgeInsets

-0.74

Wad

-0.68

(&:

-0.59

ワイイ

-0.58

 Morse

-0.58

AlterField

-0.56

 JPanel

-0.55

킨

-0.54

tola

-0.53

POSITIVE LOGITS

 Comment

1.29

 Comments

1.26

 COMMENT

1.26

 comments

1.23

 COMMENTS

1.23

Comment

1.18

Comments

1.16

 comment

1.15

comments

1.11

 commenting

1.07

Activations Density 0.149%

instances of user interaction with comments or posts

"comment" or "comments"

user comments

No Comments

No Known Activations