INDEX

Explanations

proper nouns, likely names of individuals

oai_token-act-pair · gpt-3.5-turbo

specific names, brands, or titles related to creative works or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

jac

-0.82

 chalk

-0.81

 Masquerade

-0.78

 Sabb

-0.77

 Stab

-0.73

 sprint

-0.73

 saliva

-0.72

Tec

-0.72

-0.71

Mub

-0.71

POSITIVE LOGITS

or

1.68

OR

1.53

ors

1.36

oris

1.33

Or

1.31

oros

1.29

orio

1.25

ORS

1.24

ori

1.24

orf

1.22

Activations Density 0.219%

proper nouns, likely names of individuals

specific names, brands, or titles related to creative works or media

No Comments

No Known Activations