INDEX

Explanations

phrases or words related to events occurring before something else

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "pre" in various contexts

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

IBLE

-0.70

 Shack

-0.65

 GOODMAN

-0.64

loo

-0.63

Ø©

-0.63

 realism

-0.62

 similarities

-0.61

 DRAG

-0.60

Cup

-0.60

Nig

-0.55

POSITIVE LOGITS

requisites

1.42

occup

1.32

ceed

1.30

fecture

1.28

lude

1.27

occupied

1.20

achers

1.18

clinical

1.18

cludes

1.18

req

1.18

Activations Density 0.022%

phrases or words related to events occurring before something else

occurrences of the prefix "pre" in various contexts

No Comments

No Known Activations