INDEX

Explanations

information related to directions and orientations

oai_token-act-pair · gpt-3.5-turbo

details related to positioning and orientation in a technical context

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

akings

-0.71

 Flavoring

-0.70

onut

-0.65

Skin

-0.64

ufact

-0.64

ãĥ¯ãĥ³

-0.63

 Bleach

-0.63

ologne

-0.63

ineries

-0.61

ritten

-0.60

POSITIVE LOGITS

 perpendicular

1.19

 horizontally

1.15

 perpend

1.14

 angled

1.07

 vertically

1.05

 downwards

0.95

 direction

0.95

wards

0.94

 sideways

0.94

 opposite

0.93

Activations Density 0.357%

information related to directions and orientations

details related to positioning and orientation in a technical context

No Comments

No Known Activations