INDEX

Explanations

phrases indicating uncertainty or minimal impact

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

\&

-0.50

-0.44

 bruto

-0.43

struzione

-0.43

 бъдат

-0.43

達到

-0.42

 strange

-0.42

 scientifiques

-0.42

 gerekiyor

-0.42

POSITIVE LOGITS

UnusedPrivate

0.85

providedIn

0.84

AddHtmlAttribute

0.79

 uſe

0.79

 myſelf

0.79

posedge

0.74

 pleaſure

0.73

 NSCoder

0.73

 himſelf

0.71

 itſelf

0.70

Activations Density 0.020%

phrases indicating uncertainty or minimal impact

No Comments

No Known Activations