INDEX

Explanations

indicators of structured data or code formatting

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

TagMode

-0.94

SourceChecksum

-0.85

 GenerationType

-0.79

UnsafeEnabled

-0.78

Gön

-0.77

StoryboardSegue

-0.76

($__

-0.73

Xna

-0.70

 "..\..\..\

-0.70

EndGlobalSection

-0.69

POSITIVE LOGITS

PLY

0.69

ply

0.65

Ply

0.50

hver

0.50

nore

0.49

 recordó

0.48

PRISE

0.47

Ply

0.45

uteur

0.43

ity

0.43

Activations Density 0.000%

indicators of structured data or code formatting

No Comments

No Known Activations

indicators of structured data or code formatting

No Comments

No Known Activations