INDEX

Explanations

phrases related to making and changing items or content

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

tagHelperRunner

-1.18

存于互联网档案馆

-0.92

ItemBackground

-0.89

 Baillargeon

-0.89



-0.89

تقاوى

-0.88

✨:

-0.86

RegressionTest

-0.83

 nawr

-0.82

}{*}{

-0.80

POSITIVE LOGITS

0.56

at

0.54

con

0.51

lah

0.48

 wind

0.47

0.46

 with

0.46

0.45

or

0.44

Activations Density 0.119%

phrases related to making and changing items or content

No Comments

No Known Activations