INDEX

Explanations

phrases related to demonizing or criticizing individuals or groups

oai_token-act-pair · gpt-3.5-turbo

terms associated with demonization and stigma

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ippi

-0.85

RAFT

-0.78

IGH

-0.74

ļéĨĴ

-0.71

jri

-0.69

 Soda

-0.68

 Seym

-0.67

orship

-0.67

 Seah

-0.65

 proble

-0.65

POSITIVE LOGITS

stration

1.05

iac

1.01

ises

0.96

ising

0.96

ised

0.93

izing

0.92

oid

0.91

izes

0.90

oids

0.87

ormal

0.85

Activations Density 0.008%

phrases related to demonizing or criticizing individuals or groups

terms associated with demonization and stigma

No Comments

No Known Activations