INDEX

Explanations

mathematical symbols and formatting used in equations

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

 NSCoder

-0.84

pyplot

-0.72

expects

-0.71

 McNamara

-0.70

BeginContext

-0.67

ReusableCell

-0.67

 Townsend

-0.67

 linkovi

-0.66

Parcelize

-0.65

原始内容存档于

-0.64

POSITIVE LOGITS

\;

1.30

 Doris

0.68

 sage

0.67

(";

0.65

\;

0.65

 axles

0.65

;"

0.64

الإنجليزية

0.64

 SAGE

0.64

tillery

0.63

Activations Density 0.005%

mathematical symbols and formatting used in equations

No Comments

No Known Activations