INDEX

Explanations

Twitter handles

oai_token-act-pair · gpt-3.5-turbo

underscores in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Leilan

-0.82

eteria

-0.74

 Pike

-0.72

 Turing

-0.71

 screenings

-0.68

 Juda

-0.66

quished

-0.66

 Casey

-0.66

 Levine

-0.65

 Yose

-0.65

POSITIVE LOGITS

ebook

1.27

tro

1.05

chance

0.99

pill

0.95

dust

0.95

dict

0.95

SOURCE

0.94

blank

0.93

medium

0.92

Main

0.92

Activations Density 0.022%

Twitter handles

underscores in the text

No Comments

No Known Activations