INDEX

Explanations

conjunctions 'and'

oai_token-act-pair · gpt-3.5-turbo

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

 nominate

-0.57

SPONSORED

-0.52

 marginal

-0.51

 cope

-0.49

 Aires

-0.49

¥ŀ

-0.49

 Jenner

-0.48

 redes

-0.48

er

-0.47

 Bowen

-0.47

POSITIVE LOGITS

1.10

-$

1.04

etheless

1.00

tenance

1.00

usterity

0.97

-'

0.93

lihood

0.89

_-_

0.88

-[

0.87

%-

0.85

Activations Density 0.127%

conjunctions 'and'

No Comments

No Known Activations