INDEX

Explanations

programming syntax elements and keywords used in code

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

script tags

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

URLException

-0.62

ToBounds

-0.54



-0.54

ClientRect

-0.51

UrlResolution

-0.49

 وتسجيلات

-0.48

WriteBarrier

-0.48

RegressionTest

-0.48

 IMPLIED

-0.47

EDEFAULT

-0.46

POSITIVE LOGITS

OGND

0.46

 ſta

0.40

WebElementEntity

0.40

 Jefus

0.39

 mapStateToProps

0.39

 faſt

0.36

 Houſe

0.36

 Chriſt

0.35

 divina

0.35

webElementGuid

0.34

Activations Density 0.005%

programming syntax elements and keywords used in code

script tags

No Comments

No Known Activations