INDEX

Explanations

names or titles associated with editorial roles

oai_token-act-pair · gpt-3.5-turbo

references to editors or editorial roles

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

bley

-0.80

pered

-0.76

bones

-0.71

achi

-0.71

ptoms

-0.71

enegger

-0.70

rises

-0.66

ulhu

-0.66

grades

-0.66

ffff

-0.64

POSITIVE LOGITS

ials

1.23

ially

1.14

editor

0.85

furt

0.83

 Picks

0.73

iate

0.73

ettings

0.71

rors

0.70

itatively

0.69

ienne

0.69

Activations Density 0.020%

names or titles associated with editorial roles

references to editors or editorial roles

No Comments

No Known Activations