INDEX

Explanations

phrases related to foundational concepts or criteria

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

Efq

-1.02

 pleaſure

-0.96

 myſelf

-0.91

 purpoſe

-0.91

 Theſe

-0.86

 pitié

-0.85

 Anſ

-0.85

 ſeveral

-0.83

 Reſ

-0.83

 Majefty

-0.83

POSITIVE LOGITS

PreferredItem

0.85

:✨

0.78

SharedCtor

0.77

ArgsConstructor

0.71

SourceChecksum

0.68

",{

0.66

COUVER

0.65

fillType

0.64

 TextAppearance

0.63

parsedMessage

0.63

Activations Density 0.296%

phrases related to foundational concepts or criteria

No Comments

No Known Activations

phrases related to foundational concepts or criteria

No Comments

No Known Activations