INDEX

Explanations

legal and government-related terms and actions

oai_token-act-pair · gpt-3.5-turbo

legal terms and references to legal actions or proceedings

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

Weiss

-1.02

 Weiss

-0.85

Denver

-0.81

 Asheville

-0.81

 Montana

-0.78

 Hemisphere

-0.78

 Webster

-0.77

aleigh

-0.77

 Staten

-0.76

 Florida

-0.76

POSITIVE LOGITS

jriwal

1.18

umbai

1.03

 lakh

1.01

 Hindi

1.00

 Tamil

0.99

 Sharma

0.95

 Aadhaar

0.92

Rs

0.90

 learnt

0.90

 Hindus

0.89

Activations Density 0.637%

legal and government-related terms and actions

legal terms and references to legal actions or proceedings

No Comments

No Known Activations