INDEX

Explanations

sports teams, specifically the Arizona Cardinals and Arizona Coyotes

oai_token-act-pair · gpt-3.5-turbo

mentions of specific sports teams, particularly the Cardinals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

skirts

-0.75

bered

-0.74

itness

-0.74

WARD

-0.73

lied

-0.72

encer

-0.71

auntlets

-0.70

indust

-0.68

cest

-0.67

nington

-0.67

POSITIVE LOGITS

 Cardinals

1.22

inals

0.86

 Seal

0.85

aurus

0.81

å£«

0.78

hess

0.75

 Angels

0.73

 Reds

0.71

 Lions

0.70

 Coyotes

0.70

Activations Density 0.007%

sports teams, specifically the Arizona Cardinals and Arizona Coyotes

mentions of specific sports teams, particularly the Cardinals

No Comments

No Known Activations