INDEX

Explanations

specific mentions of the location "Richmond" within the text

oai_token-act-pair · gpt-3.5-turbo

references to the location "Richmond."

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

iatrics

-0.84

ppo

-0.81

earance

-0.79

omsky

-0.75

ittance

-0.75

merce

-0.75

atched

-0.74

ãĥł

-0.74

atorial

-0.74

berman

-0.73

POSITIVE LOGITS

burgh

0.98

 Heights

0.96

 Hills

0.95

shire

0.95

 Hill

0.95

burg

0.91

 Roads

0.87

 Beach

0.79

yard

0.79

 Alley

0.77

Activations Density 0.014%

specific mentions of the location "Richmond" within the text

references to the location "Richmond."

No Comments

No Known Activations