INDEX

Explanations

mentions of organizations or entities

oai_token-act-pair · gpt-3.5-turbo

references to organizations or companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĥ´

-0.75

uckland

-0.68

bern

-0.63

inant

-0.62

rown

-0.61

icularly

-0.61

 gren

-0.61

lying

-0.59

relations

-0.59

imar

-0.59

POSITIVE LOGITS

 Foundation

0.89

 Holdings

0.82

 Laboratories

0.82

 Presents

0.81

 Publishing

0.81

Inc

0.79

 Logo

0.79

Ltd

0.78

Â®

0.77

 Corp

0.76

Activations Density 0.184%

mentions of organizations or entities

references to organizations or companies

No Comments

No Known Activations