INDEX

Explanations

instances of the word 'to' in various contexts

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

 shewn

-0.71

 Hopf

-0.68

errHandler

-0.66

PhysRevLett

-0.66

SequentialGroup

-0.65

üyada

-0.63

ęku

-0.62

 chemists

-0.62

InitVars

-0.62

jago

-0.62

POSITIVE LOGITS

 thập

0.50

ma

0.48

FromArgb

0.48

ReusableCell

0.48

toJSONString

0.47

be

0.46

 with

0.46

//</

0.46

0.45

 than

0.45

Activations Density 0.003%

instances of the word 'to' in various contexts

No Comments

No Known Activations

instances of the word 'to' in various contexts

No Comments

No Known Activations