INDEX

Explanations

phrases and terms related to statistical analysis and modeling

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

OGND

-0.69

 Winaray

-0.65

mainloop

-0.64

PageFactory

-0.60

ftagPool

-0.59

 ContentValues

-0.58

EndContext

-0.57

 esterni

-0.57

 itulah

-0.57

+#+#

-0.56

POSITIVE LOGITS

 distanciation

0.57

 equally

0.51

SafeAreaView

0.51

 similarly

0.50

miesz

0.48

rovna

0.47

attet

0.47

holtz

0.47

relevant

0.46

άνει

0.45

Activations Density 0.368%

phrases and terms related to statistical analysis and modeling

No Comments

No Known Activations