INDEX

Explanations

phrases with contrasting elements or terms

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

oun

-0.54

anwhile

-0.53

prus

-0.52

kefeller

-0.52

 Vaugh

-0.51

 namely

-0.50

 nomine

-0.49

 nodd

-0.48

"},"

-0.47

 tiss

-0.45

POSITIVE LOGITS

1.24

,,

1.10

*,

0.98

,...

0.97

.,

0.95

?,

0.92

!,

0.90

,.

0.86

%,

0.83

0.82

Activations Density 1.228%

phrases with contrasting elements or terms

No Comments

No Known Activations