INDEX

Explanations

words related to enhancement and improvement

oai_token-act-pair · gpt-3.5-turbo

technical jargon or terms related to finance, health, and legal issues

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

 Kills

-0.65

 Daylight

-0.63

enegger

-0.63

 Britann

-0.61

UTF

-0.61

 Reborn

-0.60

MEN

-0.59

©¶æ¥µ

-0.59

 Polaris

-0.59

pak

-0.58

POSITIVE LOGITS

roying

1.02

tenance

1.00

itored

1.00

acters

0.97

oldown

0.95

alog

0.88

ielding

0.88

avored

0.86

vised

0.85

ility

0.85

Activations Density 0.093%

words related to enhancement and improvement

technical jargon or terms related to finance, health, and legal issues

No Comments

No Known Activations