INDEX

Explanations

words related to legal citations and violations

oai_token-act-pair · gpt-3.5-turbo

terms related to legal violations and citations

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

sonian

-0.88

freedom

-0.84

yip

-0.83

opian

-0.82

puff

-0.78

warts

-0.78

 UNESCO

-0.77

shr

-0.75

apest

-0.73

Tea

-0.71

POSITIVE LOGITS

 Enforcement

0.98

 delinqu

0.95

 motorists

0.95

DUI

0.93

 dispatcher

0.92

 affidavit

0.92

 enforcement

0.89

 homicide

0.89

 offenses

0.87

 Officer

0.87

Activations Density 0.167%

words related to legal citations and violations

terms related to legal violations and citations

No Comments

No Known Activations