INDEX

Explanations

references to identifiers in programming or technical contexts

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

nameof, hereof, setof

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

-------

-0.49

multer

-0.47

stylers

-0.47

şört

-0.44

=[];

-0.43

]='\

-0.42

ukone

-0.42

 FILLER

-0.42

 quite

-0.42

 cooks

-0.41

POSITIVE LOGITS

nameof

2.11

 nameof

1.73

sizeof

0.76

 sizeof

0.75

setof

0.72

'{@

0.67

 ModelExpression

0.66

 AssemblyTitle

0.55

出版年

0.54

__(/*!

0.54

Activations Density 0.018%

references to identifiers in programming or technical contexts

nameof, hereof, setof

No Comments

No Known Activations