INDEX

Explanations

mentions of legal rulings or court decisions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

soever

-0.84

taboola

-0.80

 enters

-0.66

abouts

-0.66

 denotes

-0.65

stats

-0.65

bsite

-0.63

DL

-0.63

iri

-0.63

RN

-0.62

POSITIVE LOGITS

 favor

1.78

 favour

1.64

 unison

0.98

 Favor

0.96

 accordance

0.93

effect

0.91

 upholding

0.90

 vitro

0.88

 approving

0.87

clusively

0.86

Activations Density 0.114%

mentions of legal rulings or court decisions

No Comments

No Known Activations