INDEX

Explanations

mentions of physical harm or destruction by fire

oai_token-act-pair · gpt-3.5-turbo

references to fire, burning, and related injuries or destruction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

onsense

-0.75

ournal

-0.74

 reluct

-0.71

awaru

-0.69

egal

-0.68

udeau

-0.67

ensical

-0.66

alian

-0.66

ortun

-0.66

remlin

-0.65

POSITIVE LOGITS

 burning

1.14

 burn

1.12

ished

1.04

 burns

1.04

ishing

1.01

 hotter

0.99

burning

0.98

 burned

0.95

ishes

0.89

 burner

0.86

Activations Density 0.018%

mentions of physical harm or destruction by fire

references to fire, burning, and related injuries or destruction

No Comments

No Known Activations