INDEX

Explanations

phrases expressing a lack of understanding or clarity

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

URLException

-0.61

FilterChain

-0.56

ativi

-0.50

PathParam

-0.49

AutoSize

-0.47

 Anywhere

-0.47

 fact

-0.46

 utom

-0.46

utz

-0.46

InfoWindow

-0.46

POSITIVE LOGITS

évaluateur

0.78

 myſelf

0.78

 समीक्षक

0.75

^(@)

0.74

IsContent

0.74

 himſelf

0.72

تقاوى

0.72

adaptiveStyles

0.72

 Infórmanos

0.71

Населення

0.71

Activations Density 0.015%

phrases expressing a lack of understanding or clarity

No Comments

No Known Activations