INDEX

Explanations

references to specific publications or media outlets

oai_token-act-pair · gpt-3.5-turbo

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

displayText

-0.70

until

-0.70

actionDate

-0.61

command

-0.59

outside

-0.59

 unified

-0.58

forces

-0.58

near

-0.58

 awoken

-0.58

twitch

-0.58

POSITIVE LOGITS

 magazine

1.73

 Magazine

1.71

Magazine

1.47

 Publishing

1.16

 columnist

1.14

 Weekly

1.14

 magazines

1.10

 Books

1.08

 article

1.08

 Digest

1.05

Activations Density 0.157%

references to specific publications or media outlets

No Comments

No Known Activations