INDEX

Explanations

proper nouns related to recognition

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "Hon" in reference to honors or honors-related achievements

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

Negative Logits

 Apocalypse

-0.73

phrine

-0.73

 Barbarian

-0.71

 Clicker

-0.70

 Panther

-0.66

 Panic

-0.65

 Spray

-0.63

 Fired

-0.63

 Warfare

-0.62

 hypert

-0.62

POSITIVE LOGITS

orable

1.40

olulu

1.40

esty

1.20

eous

1.16

ouri

0.97

oring

0.95

iton

0.92

ored

0.91

ilo

0.90

Hon

0.90

Activations Density 0.013%

proper nouns related to recognition

phrases that include the word "Hon" in reference to honors or honors-related achievements

No Known Activations