INDEX

Explanations

references to specific US legal circuits

oai_token-act-pair · gpt-3.5-turbo

mentions of judicial circuits and legal rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ipple

-0.86

ku

-0.79

umar

-0.75

 Horus

-0.75

ighter

-0.71

wagen

-0.70

irst

-0.70

zl

-0.69

ilst

-0.68

 sacrific

-0.68

POSITIVE LOGITS

 Circuit

1.20

 Court

1.01

 circuits

0.88

 Courts

0.87

 appellate

0.87

 filings

0.84

 breaker

0.82

 circuit

0.82

 Judge

0.81

folio

0.80

Activations Density 0.012%

references to specific US legal circuits

mentions of judicial circuits and legal rulings

No Comments

No Known Activations