INDEX

Explanations

words related to mortality and medical conditions

oai_token-act-pair · gpt-3.5-turbo

references to mortality and death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

obe

-0.75

grab

-0.74

Pac

-0.74

uzz

-0.70

tag

-0.68

wire

-0.67

Pak

-0.65

brew

-0.65

wagen

-0.64

oun

-0.64

POSITIVE LOGITS

 mortality

3.75

ortality

1.78

 deaths

1.68

 death

1.53

 fatalities

1.45

 Deaths

1.42

 morbid

1.41

death

1.39

 immortality

1.26

 Mort

1.26

Activations Density 0.015%

words related to mortality and medical conditions

references to mortality and death

No Comments

No Known Activations