INDEX

Explanations

locations or place names

oai_token-act-pair · gpt-3.5-turbo

geographic locations and place names

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

imize

-0.84

ITNESS

-0.74

onym

-0.73

ILA

-0.73

 VIDEOS

-0.72

Enlarge

-0.72

 unfavorable

-0.72

externalActionCode

-0.69

aturation

-0.69

 favorable

-0.68

POSITIVE LOGITS

shire

1.23

 Albion

1.06

 Â£

1.00

 harbour

1.00

 Borough

0.99

 Harbour

0.96

 Airport

0.90

 Premiership

0.89

 Labour

0.88

 Manor

0.87

Activations Density 0.157%

locations or place names

geographic locations and place names

No Comments

No Known Activations