INDEX

Explanations

phrases containing the word "and" along with an additional concept or action

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

DX

-0.72

 Powered

-0.72

irie

-0.68

!'

-0.66

pees

-0.64

uta

-0.64

mega

-0.63

 pione

-0.62

shift

-0.62

fuck

-0.62

POSITIVE LOGITS

 therefore

1.08

 consequently

1.06

 hence

1.02

 secondly

0.95

 furthermore

0.95

 noting

0.94

 thus

0.91

 possibly

0.91

"[

0.89

 urged

0.88

Activations Density 0.305%

phrases containing the word "and" along with an additional concept or action

No Comments

No Known Activations