INDEX

Explanations

references to figures or illustrations in research documents

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

CopyWith

-0.77

 Clow

-0.70

OGND

-0.70

styleable

-0.70

httphttps

-0.64

ITT

-0.63

ScopeManager

-0.63

ViewImports

-0.61

CppMethod

-0.60

MethodManager

-0.59

POSITIVE LOGITS

ofire

0.50

 szerint

0.50

razit

0.49

如图

0.47

 будто

0.46

createCanvas

0.45

thentic

0.45

 Schmitt

0.45

Referencoj

0.43

OwnProperty

0.43

Activations Density 0.014%

references to figures or illustrations in research documents

No Comments

No Known Activations