INDEX

Explanations

references to the concept of death

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IRO

-0.82

ï¿½ï¿½ï¿½ï¿½

-0.79

âĻ

-0.73

Tex

-0.72

 enthusi

-0.71

 carp

-0.70

ï¿½ï¿½

-0.67

ims

-0.66

ë

-0.65

ìĿ

-0.65

POSITIVE LOGITS

 Death

3.84

Death

2.92

death

2.43

 death

2.40

 Deaths

2.07

 Dying

1.63

 Suicide

1.53

 deaths

1.46

 Murder

1.41

 Doom

1.40

Activations Density 0.016%

references to the concept of death

mentions of the word "Death"

No Comments

No Known Activations