INDEX

Explanations

legal or justice-related phrases

oai_token-act-pair · gpt-3.5-turbo

references to legal issues or complaints regarding rights violations

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

negie

-0.85

rontal

-0.81

":"/

-0.78

////////

-0.76

utenant

-0.76

mares

-0.72

ipel

-0.71

depending

-0.71

////////////////////////////////

-0.71

},{"

-0.71

POSITIVE LOGITS

 improperly

1.00

 incorrectly

0.93

 doct

0.86

 underage

0.84

 Yiannopoulos

0.84

 wrongly

0.82

 inappropriately

0.82

 restroom

0.81

 pornographic

0.81

 copyrighted

0.80

Activations Density 1.091%

legal or justice-related phrases

references to legal issues or complaints regarding rights violations

No Comments

No Known Activations