INDEX

Explanations

HTML attributes or tags

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

code and html syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 препратки

-0.60

ChildScrollView

-0.57

+#+#

-0.56



-0.56

 intptr

-0.56

rungsseite

-0.53

 MainAxisSize

-0.52

̍t

-0.51

 shutil

-0.51

 arşivlendi

-0.50

POSITIVE LOGITS

BibitemShut

0.64

='

0.63

=’

0.57

 للمعارف

0.55

='

0.54

=”

0.53

=\"

0.52

最快更新

0.50

bibfield

0.49

citenamefont

0.48

Activations Density 0.005%

HTML attributes or tags

code and html syntax

No Comments

No Known Activations