INDEX

Explanations

phrases related to software or product releases

oai_token-act-pair · gpt-3.5-turbo

sections of text that mark the beginning of new sentences or thoughts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lodged

-0.71

 behav

-0.70

 endors

-0.66

 nailed

-0.64

 litter

-0.64

 revoked

-0.63

 ingred

-0.63

 outwe

-0.63

dur

-0.63

 combatants

-0.63

POSITIVE LOGITS

ventory

1.48

cluding

1.38

 addition

1.26

jection

1.25

clusion

1.24

clude

1.24

cluded

1.24

juries

1.23

jury

1.22

strument

1.22

Activations Density 0.144%

phrases related to software or product releases

sections of text that mark the beginning of new sentences or thoughts

No Comments

No Known Activations