INDEX

Explanations

keywords related to prison inmates and their experiences

oai_token-act-pair · gpt-3.5-turbo

references to inmates in a correctional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pp

-0.77

rous

-0.74

opic

-0.73

 Nare

-0.70

lag

-0.70

drive

-0.68

 Obst

-0.64

Bus

-0.63

 Oslo

-0.62

OPA

-0.62

POSITIVE LOGITS

 inmates

1.22

 inmate

1.06

icts

0.93

iaries

0.85

 cylinders

0.81

 incarcerated

0.76

 closet

0.75

 prisons

0.75

 Correctional

0.74

mates

0.74

Activations Density 0.010%

keywords related to prison inmates and their experiences

references to inmates in a correctional context

No Comments

No Known Activations