INDEX

Explanations

specific measurements related to "kiln" or "kilogram."

oai_token-act-pair · gpt-3.5-turbo

references to "kilograms" or "kilns."

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

ACTED

-0.83

éĹĺ

-0.76

 Fargo

-0.68

ãģį

-0.68

 Solitaire

-0.66

 Malf

-0.66

eem

-0.63

hips

-0.63

 Guilty

-0.61

 NETWORK

-0.61

POSITIVE LOGITS

oby

1.17

patrick

1.07

ometers

1.00

oton

0.99

ogram

0.96

iman

0.95

roy

0.94

ometer

0.93

ograms

0.92

odynamic

0.88

Activations Density 0.040%

specific measurements related to "kiln" or "kilogram."

references to "kilograms" or "kilns."

No Comments

No Known Activations