INDEX

Explanations

phrases related to events resulting in harm or danger to individuals

oai_token-act-pair · gpt-3.5-turbo

references to "casual" incidents or events

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

 Mercury

-0.68

 tyrann

-0.67

unm

-0.66

 Centauri

-0.64

 fluorescent

-0.63

 prescribing

-0.62

 questioning

-0.62

 irrad

-0.59

 fixation

-0.59

 deforestation

-0.59

POSITIVE LOGITS

inelli

1.20

imir

1.10

arella

1.09

ual

1.08

cas

1.05

itaire

1.03

arro

1.03

 Royale

1.02

ierra

0.97

anova

0.96

Activations Density 0.012%

phrases related to events resulting in harm or danger to individuals

references to "casual" incidents or events

No Comments

No Known Activations