INDEX

Explanations

websites by detecting URLs starting with "www"

oai_token-act-pair · gpt-3.5-turbo

URLs that start with "www"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Ballard

-0.73

 Manifest

-0.72

 Labrador

-0.68

Vaj

-0.68

 Nadu

-0.67

 surn

-0.66

icted

-0.64

oted

-0.64

essa

-0.63

 Loans

-0.63

POSITIVE LOGITS

www

1.31

://

1.05

natureconservancy

1.03

www

1.02

twitter

0.93

forum

0.91

sites

0.89

ww

0.87

docs

0.85

doi

0.82

Activations Density 0.009%

websites by detecting URLs starting with "www"

URLs that start with "www"

No Comments

No Known Activations