INDEX

Explanations

phrases related to speeches and presentations

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

tabular

-0.55

 totalCount

-0.52

 agreement

-0.52

 literal

-0.51

 adventurers

-0.51

tyg

-0.50

 flush

-0.50

gula

-0.50

 révélé

-0.49

Agreement

-0.49

POSITIVE LOGITS

IntoConstraints

0.86

 Speeches

0.81

IndentedString

0.75

演讲

0.73

 speeches

0.70

 orator

0.68

 oration

0.66

 discursos

0.66

 Paglinawan

0.66

Vidite

0.65

Activations Density 0.026%

phrases related to speeches and presentations

No Known Activations