INDEX

Explanations

mentions of locations, specifically related to the city of Indianapolis

oai_token-act-pair · gpt-3.5-turbo

mentions of the city of Indianapolis and its associated sports teams

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

-0.88

uchin

-0.87

ramid

-0.80

ition

-0.77

ascript

-0.77

eor

-0.75

istics

-0.73

geoning

-0.72

ebook

-0.72

bley

-0.70

POSITIVE LOGITS

 Colts

1.14

apolis

1.02

 Indy

0.88

 Pacers

0.86

 Indianapolis

0.82

 Speedway

0.80

 Motor

0.74

 Eleven

0.73

 Kear

0.70

 Colt

0.70

Activations Density 0.015%

mentions of locations, specifically related to the city of Indianapolis

mentions of the city of Indianapolis and its associated sports teams

No Comments

No Known Activations