INDEX

Explanations

specific licensing or regulatory terms related to software or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tvguidetime

-0.72

jgl

-0.66

 AssemblyCulture

-0.64

 незавершена

-0.63

EndGlobalSection

-0.62

دانشنامهٔ

-0.60

ReusableCell

-0.58

 XCTest

-0.57

///</

-0.56

omock

-0.56

POSITIVE LOGITS

PrototypeOf

0.52

IsContent

0.52

Gweler

0.50

SharedCtor

0.49

 iNdEx

0.49

 textStatus

0.48

InitVars

0.48

OUBLE

0.47

 ویکی‌پدیای

0.47

↓↓↓

0.47

Activations Density 0.727%

specific licensing or regulatory terms related to software or products

No Comments

No Known Activations