INDEX

Explanations

dates and numerical values

oai_token-act-pair · gpt-3.5-turbo

references to numerical values or quantities

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

indal

-0.62

wcs

-0.62

 Barbar

-0.62

gencies

-0.62

vation

-0.61

 Grind

-0.59

 Goodbye

-0.58

 Mour

-0.58

inness

-0.58

ggle

-0.57

POSITIVE LOGITS

 encoding

0.69

=-

0.66

channelAvailability

0.64

phis

0.61

 computing

0.58

 transcript

0.53

olin

0.53

};

0.53

 redacted

0.52

Activations Density 0.195%

dates and numerical values

references to numerical values or quantities

No Comments

No Known Activations