INDEX

Explanations

references to mathematical variables or symbols

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

 kaynağından

-0.78

لينكات

-0.73

 Nagar

-0.72

︎

-0.71

Sigue

-0.69

 malen

-0.66

 للاسماء

-0.66

didSet

-0.65

 setUp

-0.64

tôi

-0.64

POSITIVE LOGITS

Phi

1.31

 Phipps

1.17

Phi

1.02

Frankie

0.88

 Ques

0.87

 Brookfield

0.87

Φ

0.85

 Philos

0.81

лектро

0.79

 Bellini

0.79

Activations Density 0.018%

references to mathematical variables or symbols

No Comments

No Known Activations