INDEX

Explanations

mathematical expressions and notations related to functions and scaling laws

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

kus

-0.48

 Sonne

-0.48

Fast

-0.47

 Fast

-0.46

new

-0.45

acán

-0.45

ρός

-0.44

sm

-0.43

aneo

-0.43

ΗΣ

-0.43

POSITIVE LOGITS

 kasarigan

1.00

IsMutable

0.93

 مشين

0.93

MessageOf

0.92

 виправивши

0.84

ConstraintMaker

0.79

msgTypes

0.78

Демографія

0.78

CloseOperation

0.77

 فريبيس

0.77

Activations Density 0.264%

mathematical expressions and notations related to functions and scaling laws

No Comments

No Known Activations