INDEX

Explanations

quotations from individuals

oai_token-act-pair · gpt-3.5-turbo

quotes from speakers

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

spir

-0.85

successfully

-0.83

 interfered

-0.81

mol

-0.79

à¼

-0.79

ãĥİ

-0.79

artifacts

-0.77

endars

-0.77

etheless

-0.74

Login

-0.74

POSITIVE LOGITS

Sgt

1.05

 Diane

1.03

Dr

1.02

Mr

0.97

Ms

0.96

 Chris

0.96

Lt

0.95

 Mike

0.95

 Geoff

0.95

Tom

0.94

Activations Density 0.056%

quotations from individuals

quotes from speakers

No Comments

No Known Activations