INDEX

Explanations

programming-related terminology and actions

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

of

-0.59

 time

-0.51

 Time

-0.51

time

-0.50

pen

-0.49

感じる

-0.49

見える

-0.48

 string

-0.47

cheln

-0.47

ind

-0.47

POSITIVE LOGITS

OGND

0.90

UserScript

0.81

 nahilalakip

0.79

 itſelf

0.79

 "..\..\..\

0.78

RectangleBorder

0.78

rentices

0.77

LookAnd

0.75

 mergeFrom

0.75

".

0.75

Activations Density 0.019%

programming-related terminology and actions

No Comments

No Known Activations