INDEX

Explanations

words that convey a sense of legal proceedings or evaluations related to medical conditions

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

OGND

-0.93

AccessorTable

-0.92

extAlignment

-0.89

 nahilalakip

-0.87

 تضيفلها

-0.78

 estimés

-0.77

WebVitals

-0.76

 doInBackground

-0.76

帖最后由

-0.76

ViewChild

-0.75

POSITIVE LOGITS

fuck

0.49

Fuck

0.48

FUCK

0.48

 FUCK

0.47

0.46

<blockquote>

0.46

 Fuck

0.43

icago

0.42

 yür

0.42

 Pingback

0.42

Activations Density 0.014%

words that convey a sense of legal proceedings or evaluations related to medical conditions

No Comments

No Known Activations