INDEX

Explanations

terms related to prisons and incarceration

oai_token-act-pair · gpt-3.5-turbo

references to prisons and the prison system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lass

-0.80

thora

-0.75

yip

-0.74

rians

-0.71

rian

-0.68

ï¸ı

-0.67

witz

-0.65

sound

-0.65

abeth

-0.64

£ı

-0.64

POSITIVE LOGITS

 inmates

1.04

 inmate

0.96

 sentences

0.88

 prisons

0.87

 prisoners

0.86

prison

0.84

house

0.81

 prison

0.81

 Guantanamo

0.81

 rehabilitation

0.79

Activations Density 0.043%

terms related to prisons and incarceration

references to prisons and the prison system

No Comments

No Known Activations