INDEX

Explanations

non-alphanumeric characters

oai_token-act-pair · gpt-3.5-turbo

the presence of undefined or empty content

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 brunt

-0.75

hement

-0.71

 Cent

-0.66

 aging

-0.66

 blinded

-0.66

 intervening

-0.65

 amnesty

-0.65

 diseng

-0.65

 estranged

-0.65

 Dollar

-0.64

POSITIVE LOGITS

ÂłÂłÂł

1.23

ÂłÂłÂłÂł

1.07

FactoryReloaded

1.07

ÂłÂłÂłÂłÂłÂłÂłÂł

1.02

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

1.02

pmwiki

0.98

ÂłÂł

0.95

Anonymous

0.92

roo

0.91

à¨

0.90

Activations Density 0.226%

non-alphanumeric characters

the presence of undefined or empty content

No Comments

No Known Activations