INDEX

Explanations

terms associated with legal claims and assertions

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

contentLoaded

-0.74

Dowell

-0.68

 McDowell

-0.68

dshaw

-0.67

––––

-0.66

évaluateur

-0.65

はじめに

-0.62

 faço

-0.62

Guido

-0.62

########.

-0.61

POSITIVE LOGITS

 asserting

0.85

 asserts

0.83

 Assertion

0.82

rungsseite

0.79

Portail

0.76

 assertion

0.75

 asserted

0.75

 assertions

0.75

 Asser

0.74

theit

0.73

Activations Density 0.012%

terms associated with legal claims and assertions

No Comments

No Known Activations