INDEX

Explanations

references to different US Court of Appeals circuits and related legal terms

oai_token-act-pair · gpt-3.5-turbo

references to courts and legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Remem

-0.84

udeau

-0.79

 Horus

-0.79

ku

-0.77

eem

-0.76

byn

-0.75

tsky

-0.74

tein

-0.72

 Weasley

-0.72

ombies

-0.69

POSITIVE LOGITS

 sided

0.98

 judge

0.97

 justices

0.97

Court

0.95

 appellate

0.93

Judge

0.87

 Judge

0.84

 rulings

0.83

jud

0.82

orneys

0.81

Activations Density 0.053%

references to different US Court of Appeals circuits and related legal terms

references to courts and legal proceedings

No Comments

No Known Activations