INDEX

Explanations

phrases related to legal or legislative text

oai_token-act-pair · gpt-3.5-turbo

legal terminology and references to statutes or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Oops

-0.83

ï¸ı

-0.73

elight

-0.71

 Frie

-0.71

ideos

-0.63

pictured

-0.61

alkyrie

-0.61

 Goodbye

-0.61

odox

-0.60

RH

-0.59

POSITIVE LOGITS

 subparagraph

1.21

 hereby

1.18

 shall

1.15

``(

1.10

[[

1.09

:(

1.09

'';

1.08

 notwithstanding

1.08

<<

1.07

''.

1.07

Activations Density 0.315%

phrases related to legal or legislative text

legal terminology and references to statutes or regulations

No Comments

No Known Activations