INDEX

Explanations

lawyers or legal professionals mentioned in a text

oai_token-act-pair · gpt-3.5-turbo

references to legal professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

plings

-0.93

oppers

-0.80

urat

-0.76

auri

-0.72

ween

-0.72

wn

-0.71

pora

-0.71

bows

-0.70

inki

-0.69

aukee

-0.67

POSITIVE LOGITS

itatively

0.85

 examiner

0.84

hood

0.82

suit

0.78

 Sergei

0.75

 lawyer

0.74

yer

0.74

ate

0.73

 solicitor

0.72

ess

0.71

Activations Density 0.026%

lawyers or legal professionals mentioned in a text

references to legal professionals

No Comments

No Known Activations