INDEX

Explanations

health-related issues and negative outcomes

oai_token-act-pair · gpt-3.5-turbo

terms associated with health risks, particularly cancer and pregnancy-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

raid

-0.62

 Czech

-0.60

LESS

-0.58

Rocket

-0.57

entity

-0.56

 corridor

-0.55

 agent

-0.54

 Hudson

-0.54

Technology

-0.53

 guid

-0.52

POSITIVE LOGITS

uggest

1.22

ettings

1.12

hips

1.03

paces

0.94

chool

0.86

igmatic

0.84

hip

0.83

cies

0.82

ongs

0.82

cape

0.81

Activations Density 0.130%

health-related issues and negative outcomes

terms associated with health risks, particularly cancer and pregnancy-related topics

No Comments

No Known Activations