INDEX

Explanations

honors and awards

oai_token-act-pair · gpt-3.5-turbo

references to honors and accolades

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

 Apocalypse

-0.70

 Panther

-0.69

Zot

-0.68

 Annotations

-0.68

 Barbarian

-0.67

phrine

-0.67

 Printed

-0.66

 Bernstein

-0.66

 Panic

-0.66

 Clicker

-0.64

POSITIVE LOGITS

olulu

1.38

orable

1.33

eous

1.22

esty

1.16

anced

1.03

enge

0.95

ouri

0.95

eteenth

0.93

oring

0.93

ably

0.92

Activations Density 0.014%

honors and awards

references to honors and accolades

No Comments

No Known Activations