INDEX

Explanations

terms related to legal issues, specifically indictments

oai_token-act-pair · gpt-3.5-turbo

terms related to legal charges or accusations, specifically indictments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

birth

-0.84

 lear

-0.79

ijk

-0.70

istic

-0.69

 Rapt

-0.68

 Trick

-0.65

istically

-0.65

iman

-0.65

 Kers

-0.64

 Dragonbound

-0.63

POSITIVE LOGITS

 indict

1.20

eering

1.17

 indictment

1.16

 indicted

1.09

 alleges

0.92

ments

0.91

 warrant

0.90

 accuses

0.87

 unse

0.87

 warrants

0.86

Activations Density 0.037%

terms related to legal issues, specifically indictments

terms related to legal charges or accusations, specifically indictments

No Comments

No Known Activations