INDEX

Explanations

terms related to freezing and frozen states

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

Ats

-0.86

########.

-0.84

 mourut

-0.82

retudo

-0.82

 tegens

-0.81

!("{}",

-0.79

NCT

-0.76

 useAppContext

-0.75

 <=",

-0.75

migrationBuilder

-0.75

POSITIVE LOGITS

 Freeze

1.09

 freeze

1.05

Freeze

0.93

 freezes

0.87

 frozen

0.85

freeze

0.85

 freezing

0.84

 froze

0.84

 congel

0.78

 Baumann

0.78

Activations Density 0.005%

terms related to freezing and frozen states

No Known Activations