INDEX

Explanations

code-related syntax and structure within documentation

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

 ModelExpression

-1.14

bootstrapcdn

-1.05

Personensuche

-1.02

ReusableCell

-1.01

ContentAsync

-1.00

LookAnd

-0.97

windowFixed

-0.96

 ویکی‌پدی

-0.95

BufferException

-0.94

 typelib

-0.94

POSITIVE LOGITS

((

0.56

 kole

0.50

 Independent

0.47

هات

0.46

 defending

0.46

Unmarshal

0.45

_{

0.44

 lisää

0.43

Activations Density 0.024%

code-related syntax and structure within documentation

No Comments

No Known Activations

code-related syntax and structure within documentation

No Comments

No Known Activations