INDEX

Explanations

mentions of the city name "Cincinnati" and possibly sports teams or related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of Cincinnati and its associated sports teams or events

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

vana

-0.86

pring

-0.80

bes

-0.77

ledged

-0.76

iating

-0.75

ially

-0.75

eways

-0.74

lasses

-0.73

ariat

-0.72

inal

-0.71

POSITIVE LOGITS

 Bengals

1.10

 Reds

1.00

incinn

0.94

 Cincinnati

0.88

hurst

0.78

incinnati

0.77

 Parks

0.71

 Bengal

0.70

Zoo

0.70

 Jail

0.68

Activations Density 0.013%

mentions of the city name "Cincinnati" and possibly sports teams or related terms

mentions of Cincinnati and its associated sports teams or events

No Comments

No Known Activations