INDEX

Explanations

filenames and file extensions related to various document types and software components

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

file extensions

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

 nahilalakip

-0.95

 للمعارف

-0.90

tagHelperRunner

-0.88

 المعيارى

-0.82

 kaynağından

-0.79

__":

-0.79

出版年

-0.76

ValueStyle

-0.76

rungsseite

-0.75

Życiorys

-0.73

POSITIVE LOGITS

<strong>

0.41

0.40

0.38

”

0.38

0.36

0.35

 Gold

0.34

0.33

Ch

0.32

Activations Density 0.043%

filenames and file extensions related to various document types and software components

file extensions

No Comments

No Known Activations