INDEX

Explanations

key issues and performance metrics in a range of contexts

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

app store and publication

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

 ModelExpression

-0.60

WebElementEntity

-0.57

 désolés

-0.54

 <>",

-0.53

 defaultstate

-0.52

fromnode

-0.52

Chham

-0.52

 cherchés

-0.50

 canst

-0.50

сылкі

-0.50

POSITIVE LOGITS

esModule

0.36

Ậ

0.36

 Papp

0.35

OK

0.33

 FIGURE

0.31

FIGURE

0.31

ury

0.31

Kle

0.31

rating

0.30

 stock

0.30

Activations Density 0.377%

key issues and performance metrics in a range of contexts

app store and publication

No Comments

No Known Activations