INDEX

Explanations

numbers and related statistical values

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

numerical values and locations

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

 kasarigan

-0.43

evos

-0.35

ASU

-0.33

 shall

-0.33

ﬅ

-0.32

 HasFactory

-0.32

SourceChecksum

-0.31



-0.31

 sẻ

-0.31

ніципалі

-0.31

POSITIVE LOGITS

 تضيفلها

0.61

Tembelea

0.56

 विश्वसनीयता

0.52

ViewImports

0.52

 Paglinawan

0.52

 ब्रेकडाउन

0.51

 ſeveral

0.51

 ModelExpression

0.50

rungsseite

0.48

ImageContext

0.48

Activations Density 0.106%

numbers and related statistical values

numerical values and locations

No Comments

No Known Activations