INDEX

Explanations

phrases or terms formatted as mathematical questions or statements related to factors and multiples

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

 calendriers

-0.80

TintMode

-0.64

enderror

-0.62

oredCriteria

-0.60

++];

-0.59

WriteTagHelper

-0.59

 chofe

-0.57

 lenker

-0.56

ThroughAttribute

-0.56

 kiệm

-0.56

POSITIVE LOGITS

not

0.70

RegistryLite

0.66

is

0.60

Is

0.60

can

0.56

0.55

su

0.55

serviceWorker

0.55

en

0.52

 does

0.52

Activations Density 0.088%

phrases or terms formatted as mathematical questions or statements related to factors and multiples

No Comments

No Known Activations