INDEX

Explanations

commonly referenced but unspecified items or things

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

CVE

-0.67

externalActionCode

-0.66

 Examination

-0.66

 srfAttach

-0.65

vette

-0.63

emale

-0.63

 crest

-0.62

 captcha

-0.59

bered

-0.59

INAL

-0.58

POSITIVE LOGITS

bags

1.11

 happening

1.03

 happens

1.00

hots

0.97

ious

0.91

bag

0.90

0.89

iness

0.89

 else

0.87

smanship

0.86

Activations Density 0.039%

commonly referenced but unspecified items or things

No Comments

No Known Activations