INDEX

Explanations

items or objects that are being described or mentioned

oai_token-act-pair · gpt-3.5-turbo

relative clauses or descriptive phrases in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

done

-0.68

doing

-0.66

anton

-0.64

 mindful

-0.63

 VIDEOS

-0.63

————

-0.63

ional

-0.61

 focusing

-0.60

 Thoughts

-0.60

ONE

-0.59

POSITIVE LOGITS

 resembles

1.11

 protr

1.08

 belonged

1.02

 attaches

1.01

 corresponds

1.01

 weighs

1.00

 accompanies

1.00

 belongs

0.99

 sits

0.95

 emits

0.95

Activations Density 0.221%

items or objects that are being described or mentioned

relative clauses or descriptive phrases in the text

No Comments

No Known Activations