INDEX

Explanations

law enforcement-related terms, particularly mentioning "deputies"

oai_token-act-pair · gpt-3.5-turbo

mentions of law enforcement officials

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ebook

-0.86

FORE

-0.84

ces

-0.76

¥µ

-0.75

hetti

-0.73

drive

-0.71

gged

-0.71

eb

-0.70

church

-0.70

Virgin

-0.69

POSITIVE LOGITS

 deputies

1.18

 confir

1.01

 sheriff

0.89

uty

0.87

uties

0.84

 sher

0.83

ixel

0.79

 handlers

0.78

 detained

0.76

 dispatcher

0.74

Activations Density 0.008%

law enforcement-related terms, particularly mentioning "deputies"

mentions of law enforcement officials

No Known Activations