INDEX

Explanations

names of individuals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orter

-0.80

fax

-0.78

essee

-0.72

*/(

-0.70

orters

-0.70

ffee

-0.68

edom

-0.65

ete

-0.65

¶æ

-0.64

natureconservancy

-0.63

POSITIVE LOGITS

wered

0.88

orne

0.76

enegger

0.76

senal

0.75

Kut

0.74

Ans

0.74

ammers

0.74

 Loren

0.71

azar

0.71

gets

0.69

Activations Density 0.165%

names of individuals

No Comments

No Known Activations