INDEX

Explanations

characters that correspond to mathematical operations or variables

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

 plan

-0.43

tvguidetime

-0.41

kus

-0.40

 precisar

-0.40

sep

-0.40

出版年

-0.40

 quema

-0.39

 relever

-0.39

pland

-0.39

 план

-0.39

POSITIVE LOGITS

 AssemblyCulture

0.85

yntaxException

0.84

bootstrapcdn

0.79

RectangleBorder

0.79

resave

0.78

 مواليد

0.77

IsMutable

0.76

InvalidProtocol

0.75

 houſe

0.75

 themſelves

0.75

Activations Density 0.009%

characters that correspond to mathematical operations or variables

No Comments

No Known Activations

characters that correspond to mathematical operations or variables

No Comments

No Known Activations