INDEX

Explanations

legal terms and court-related phrases

oai_token-act-pair · gpt-3.5-turbo

references to legal terminology or proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mosqu

-0.87

 dumps

-0.82

 uranium

-0.72

 donate

-0.72

 wellness

-0.71

 congratulations

-0.71

 beaut

-0.71

 banana

-0.70

 favourite

-0.70

 disaster

-0.69

POSITIVE LOGITS

Footnote

1.10

âĢł

1.05

Â§

1.04

Â¶

0.98

¤

0.92

º

0.87

Court

0.84

ÂłÂłÂłÂłÂłÂłÂłÂł

0.84

âĨĳ

0.84

âĢ¢âĢ¢

0.83

Activations Density 0.409%

legal terms and court-related phrases

references to legal terminology or proceedings

No Comments

No Known Activations