INDEX

Explanations

relevant mentions of peer-reviewed articles or studies within scientific literature

oai_token-act-pair · gpt-3.5-turbo

terms associated with academic publishing and peer review

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Battery

-0.87

 totem

-0.84

 charms

-0.82

 Patriot

-0.78

atra

-0.75

riot

-0.73

Lago

-0.72

asonic

-0.72

ebus

-0.70

apon

-0.69

POSITIVE LOGITS

 PubMed

1.06

Study

0.96

 journals

0.95

 peer

0.92

 studies

0.92

 publication

0.91

 biomedical

0.90

 scholarly

0.87

 journal

0.86

 study

0.86

Activations Density 0.174%

relevant mentions of peer-reviewed articles or studies within scientific literature

terms associated with academic publishing and peer review

No Comments

No Known Activations