INDEX

Explanations

names of publications or media outlets followed by interviews

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

TRY

-0.80

ãĤ¦ãĤ¹

-0.74

displayText

-0.74

ongevity

-0.73

rats

-0.70

vec

-0.70

agram

-0.70

othal

-0.68

osc

-0.66

$$$$

-0.64

POSITIVE LOGITS

 spokesperson

0.93

 however

0.86

 spokesman

0.84

 spokeswoman

0.84

 meanwhile

0.80

 dated

0.79

 Greenwald

0.78

CEO

0.76

 citing

0.73

 former

0.72

Activations Density 0.103%

names of publications or media outlets followed by interviews

No Comments

No Known Activations