INDEX

Explanations

references to lessons learned from experiences or mistakes

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

Negative Logits

andExpect

-0.65

netinet

-0.65

 stö

-0.58

Chham

-0.56

complexContent

-0.56

ργο

-0.56

 newBuilder

-0.55

 Himo

-0.53

 aload

-0.52

 Bland

-0.52

POSITIVE LOGITS

 lessons

0.92

Lessons

0.88

 Lessons

0.88

lessons

0.80

 learnings

0.80

 experience

0.79

experience

0.75

 опыт

0.75

 erfaring

0.74

 Erfahrungen

0.74

Activations Density 0.044%

references to lessons learned from experiences or mistakes

No Known Activations