INDEX

Explanations

programming syntax and structure

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

sets, clauses, punctuation

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

Chham

-0.73

تقاوى

-0.72

 otomatig

-0.71

 دیکھیے

-0.68

IndentedString

-0.65

 Wiktionnaire

-0.63

########.

-0.62

Jîn

-0.62

OGND

-0.62

 INTERESAR

-0.62

POSITIVE LOGITS

TypedDataSet

0.59

 betweenstory

0.38

ViewImports

0.34

codecSelfer

0.31

 Post

0.30

做到

0.30

$(

0.30

은

0.30

 angen

0.29

 nonUne

0.29

Activations Density 0.052%

programming syntax and structure

sets, clauses, punctuation

No Comments

No Known Activations