INDEX

Explanations

complex nested structures or lists in textual data

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

Negative Logits

 تانيه

-0.64

mbrie

-0.56

mbra

-0.51

EnableWeb

-0.49

nambuco

-0.48

sbereich

-0.46

 tetrachloride

-0.45

נוּ

-0.45

 gern

-0.45

esModule

-0.44

POSITIVE LOGITS

setVerticalGroup

0.66

DockStyle

0.65

featureID

0.63

 AssemblyCulture

0.63

ObjectModel

0.62

BeginInit

0.62

 Италијани

0.62

 consultato

0.59

Abitanti

0.58

InitVars

0.58

Activations Density 0.055%

complex nested structures or lists in textual data

No Known Activations