INDEX

Explanations

indicators of boolean flags and their states in code

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

boolean values

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

InputBorder

-0.40

 abstracts

-0.40

 Rivas

-0.39

ukin

-0.38

RectangleBorder

-0.37

Domestic

-0.36

而来

-0.36

Bib

-0.36

 Gran

-0.36

 domestic

-0.36

POSITIVE LOGITS

الحياه

0.50

帖最后由

0.50

+#+

0.48

stdbool

0.48

LookAnd

0.48

pecabe

0.47

 Infórmanos

0.47

rrggbb

0.47

 ujednoznacz

0.47

 pinulongan

0.46

Activations Density 0.011%

indicators of boolean flags and their states in code

boolean values

No Comments

No Known Activations