INDEX

Explanations

terms related to law enforcement and government

oai_token-act-pair · gpt-3.5-turbo

mentions of police and government entities

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igmatic

-0.88

weet

-0.80

bits

-0.72

stones

-0.72

bles

-0.69

ãĥĨãĤ£

-0.69

itatively

-0.69

paste

-0.68

greg

-0.68

icol

-0.68

POSITIVE LOGITS

 judiciary

1.30

 prosecutors

1.25

 prosecut

1.17

 firefighters

1.14

 sheriff

1.11

DEA

1.07

FBI

1.07

 ambulance

1.04

 civilian

1.04

 academia

1.04

Activations Density 0.191%

terms related to law enforcement and government

mentions of police and government entities

No Comments

No Known Activations