INDEX

Explanations

terms related to law enforcement and legal proceedings

oai_token-act-pair · gpt-3.5-turbo

mentions of legal proceedings or criminal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Kansas

-0.97

Newsletter

-0.94

-0.86

Atlanta

-0.78

Zip

-0.77

Arizona

-0.76

 favored

-0.76

Chicago

-0.75

Ohio

-0.72

-0.71

POSITIVE LOGITS

 criticised

1.17

 organisers

1.16

 analys

1.12

mum

1.11

 paed

1.09

 analyse

1.07

 offences

1.06

 apologised

1.06

 realise

1.03

 barr

0.99

Activations Density 1.158%

terms related to law enforcement and legal proceedings

mentions of legal proceedings or criminal activities

No Comments

No Known Activations