INDEX

Explanations

numerical values and their associated contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ftagPool

-0.63

 désolés

-0.55

elemField

-0.55

bootstrapcdn

-0.54

lahraga

-0.51

Parcelable

-0.50

 loosing

-0.49

chapper

-0.48

 Erde

-0.47

 transférez

-0.47

POSITIVE LOGITS

FunctionFlags

0.64

UnknownFieldSet

0.59

tagHelperRunner

0.58

Kof

0.57

ThroughAttribute

0.57

 Bourgoin

0.57

pédie

0.56

audiovisuel

0.55

 EconPapers

0.55

MemoryWarning

0.54

Activations Density 0.390%

numerical values and their associated contexts

No Comments

No Known Activations