INDEX

Explanations

technical terms and abbreviations related to a specific field, possibly related to computing or engineering

oai_token-act-pair · gpt-3.5-turbo

references to specific electronic communication systems or protocols

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ciation

-0.89

esthetic

-0.77

pocket

-0.73

 ç¥ŀ

-0.71

 Jagu

-0.70

creen

-0.69

 Flavoring

-0.68

tenance

-0.66

 Hots

-0.65

cific

-0.65

POSITIVE LOGITS

redits

0.95

ritical

0.94

ORD

0.86

outer

0.86

LECT

0.84

MAS

0.84

oin

0.83

ERN

0.83

overed

0.82

onut

0.82

Activations Density 0.016%

technical terms and abbreviations related to a specific field, possibly related to computing or engineering

references to specific electronic communication systems or protocols

No Comments

No Known Activations