INDEX

Explanations

terms related to mathematical expressions and variables in statistical 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

 referenties

-0.68

RenderAtEndOf

-0.68

Lie

-0.50

Lie

-0.50

 Lieberman

-0.46

 CreateTagHelper

-0.46

risti

-0.46

 Kerja

-0.45

Numerous

-0.45

 Multiple

-0.44

POSITIVE LOGITS

IntoConstraints

0.81

WebControls

0.69

 rôles

0.63

 répartition

0.63

Hauptartikel

0.59

fficients

0.57

̈́

0.56

ConstraintMaker

0.56

IsMutable

0.55

 proportions

0.55

Activations Density 0.435%

terms related to mathematical expressions and variables in statistical contexts

No Comments

No Known Activations