INDEX

Explanations

names of individuals, specifically focusing on the name "Margaret."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Margaret."

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

hma

-0.89

enegger

-0.88

EStreamFrame

-0.86

perse

-0.81

ptroller

-0.77

footed

-0.77

cript

-0.77

pmwiki

-0.77

ngth

-0.77

INESS

-0.76

POSITIVE LOGITS

 Thatcher

1.27

 Margaret

1.01

aret

0.87

 Rodham

0.82

 Downs

0.81

 McMahon

0.78

 Keane

0.76

 Chamberlain

0.76

 Anne

0.75

 Sloan

0.75

Activations Density 0.013%

names of individuals, specifically focusing on the name "Margaret."

mentions of the name "Margaret."

No Comments

No Known Activations