INDEX

Explanations

terms related to poverty

oai_token-act-pair · gpt-3.5-turbo

references to poverty and its impact on society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ERC

-0.77

ergy

-0.73

£ı

-0.73

assador

-0.68

ateur

-0.67

natureconservancy

-0.67

wcsstore

-0.66

Sphere

-0.66

ube

-0.66

ITNESS

-0.65

POSITIVE LOGITS

 allev

1.23

 stricken

1.11

 poverty

0.92

 wages

0.87

 erad

0.84

overty

0.83

 ridden

0.81

 wage

0.77

 endemic

0.76

 relief

0.76

Activations Density 0.041%

terms related to poverty

references to poverty and its impact on society

No Comments

No Known Activations