INDEX

Explanations

instances of access modifiers in code

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

private static

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

𓃵

-0.40

tvguidetime

-0.36

RenderAtEndOf

-0.35

 הזה

-0.35

 nahilalakip

-0.33

titleMargin

-0.33

SharedDtor

-0.33

 hueso

-0.33

 cara

-0.32

多了

-0.32

POSITIVE LOGITS

 static

1.20

static

0.99

 themselves

0.95

 itself

0.94

 herself

0.87

themselves

0.81

 himself

0.81

itself

0.79

himself

0.74

 Itself

0.73

Activations Density 0.001%

instances of access modifiers in code

private static

No Comments

No Known Activations