INDEX

Explanations

programming-related syntax and structure in code snippets

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

ː

-0.48

ger

-0.47

centage

-0.46

ectoria

-0.44

 volna

-0.42

Kontrola

-0.42

 prevista

-0.40

inear

-0.40

NewReader

-0.40

 spéciaux

-0.39

POSITIVE LOGITS

LookAnd

0.96

__':

0.90

 betweenstory

0.74

 unknownFields

0.71

таратура

0.71

__':

0.71

 mergeFrom

0.70

QMetaType

0.70

utilisons

0.69

esac

0.68

Activations Density 0.005%

programming-related syntax and structure in code snippets

No Comments

No Known Activations