INDEX

Explanations

long-term references or descriptions

oai_token-act-pair · gpt-3.5-turbo

references to long-term concepts or periods

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Compass

-0.91

 Scrib

-0.88

 Polo

-0.80

Pok

-0.78

 Clubs

-0.74

 Solitaire

-0.72

 Brooke

-0.72

 Morrow

-0.65

 GOODMAN

-0.65

 GEAR

-0.64

POSITIVE LOGITS

term

1.55

lasting

1.42

awaited

1.34

lived

1.30

distance

1.25

haired

1.24

established

1.21

range

1.21

serving

1.19

Term

1.19

Activations Density 0.038%

long-term references or descriptions

references to long-term concepts or periods

No Comments

No Known Activations