INDEX

Explanations

sections of code related to definitions, methods, and errors in programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ानी

-0.53

 elé

-0.48

 flesta

-0.46

 Mantle

-0.44

 maschile

-0.43

 établie

-0.42

 care

-0.42

ApiOperation

-0.41

ximadamente

-0.40

 middag

-0.39

POSITIVE LOGITS

SequentialGroup

0.89

 تضيفلها

0.81

 pinulongan

0.81

 ISNI

0.70

الإنجليزية

0.70

+#+#

0.69

Autoritní

0.67

Ārējās

0.66

webElementXpaths

0.65

writeFieldEnd

0.65

Activations Density 0.288%

sections of code related to definitions, methods, and errors in programming constructs

No Comments

No Known Activations