INDEX

Explanations

technical and scientific terms related to typesetting and printing processes

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

+#+#

-0.93

-0.91

 kasarigan

-0.90

帖最后由

-0.82

 >=",

-0.81

extAlignment

-0.80

endpush

-0.80

__(/*!

-0.78

JspWriter

-0.77

 CreateTagHelper

-0.76

POSITIVE LOGITS

 Diſ

0.68

 themſelves

0.67

 ſche

0.65

 itſelf

0.65

 Majefty

0.63

 ſever

0.63

 Chriftian

0.62

 ―――――

0.60

 himſelf

0.59

 ་་

0.59

Activations Density 18.504%

technical and scientific terms related to typesetting and printing processes

No Comments

No Known Activations