INDEX

Explanations

mentions of correctional facilities or departments

oai_token-act-pair · gpt-3.5-turbo

references to correctional facilities and the corrections system

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

issan

-0.76

 Mits

-0.71

 Sparkle

-0.68

founded

-0.68

 spirited

-0.68

ded

-0.66

amd

-0.65

ding

-0.65

spring

-0.64

rous

-0.64

POSITIVE LOGITS

 Corrections

1.07

 prisons

0.97

 Correctional

0.97

 jails

0.94

 correctional

0.84

 Facility

0.81

 corrections

0.79

 incarcer

0.79

chwitz

0.78

 Institution

0.76

Activations Density 0.011%

mentions of correctional facilities or departments

references to correctional facilities and the corrections system

No Comments

No Known Activations