INDEX

Explanations

code-related elements and programming syntax

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

code includes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

CloseOperation

-0.66

 EconPapers

-0.56

InjectAttribute

-0.52

DockStyle

-0.52

 StatelessWidget

-0.47

UpInside

-0.47

InitStruct

-0.47

 BoxFit

-0.45

AnchorStyles

-0.45

OGND

-0.44

POSITIVE LOGITS

stdc

0.50

########.

0.49

bootstrapcdn

0.47

Numerade

0.46

 afgelopen

0.40

 zijne

0.36

er

0.35

ヮ

0.35

 zoude

0.35

śni

0.35

Activations Density 0.008%

code-related elements and programming syntax

code includes

No Comments

No Known Activations