INDEX

Explanations

terms related to data manipulation or programming concepts

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

WithIOException

-0.91

ViewFeatures

-0.82

ANTLR

-0.79

Diweddarwch

-0.77

 Roskov

-0.75

GraphicsUnit

-0.71

Демографія

-0.71

tagHelperRunner

-0.70

 للمعارف

-0.69

providedIn

-0.68

POSITIVE LOGITS

 estimés

0.49

ίνει

0.48

ůj

0.47

CastException

0.47

unately

0.47

IsContent

0.45

ictwo

0.45

 néz

0.45

 dasarnya

0.44

 lautet

0.43

Activations Density 0.001%

terms related to data manipulation or programming concepts

No Comments

No Known Activations