INDEX

Explanations

references to user interface elements in programming documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Smal

-0.74

MIDDLEWARE

-0.64

orious

-0.64

 Besch

-0.62

 Kearney

-0.61

Belf

-0.60

 Desai

-0.58

utton

-0.58

rawler

-0.56

 primo

-0.56

POSITIVE LOGITS

Name

1.20

 ModelExpression

0.84

simpleType

0.83

AndEndTag

0.83

ly

0.78

BeginContext

0.77

 onData

0.76

}{||

0.75

 rempliss

0.74

enumii

0.74

Activations Density 0.044%

references to user interface elements in programming documentation

No Comments

No Known Activations