INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "BUR"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

oral

-0.78

hover

-0.74

 Martial

-0.72

wine

-0.72

uve

-0.68

ORGE

-0.66

 temper

-0.63

 impression

-0.63

 Mach

-0.62

 seas

-0.62

POSITIVE LOGITS

ity

1.16

ities

0.95

acters

0.85

itous

0.84

ITY

0.81

myra

0.80

etsk

0.79

erick

0.78

itar

0.78

isu

0.77

Activations Density 0.030%

proper nouns

mentions of the word "BUR"

No Comments

No Known Activations