INDEX

Explanations

phrases related to disclosure of personal information

oai_token-act-pair · gpt-3.5-turbo

references to confessions or acts of admitting wrongdoing

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

 impacted

-0.81

 Phase

-0.81

 impacts

-0.80

 Impact

-0.79

 impact

-0.79

impact

-0.68

 Riders

-0.67

raviolet

-0.67

agnetic

-0.66

alf

-0.64

POSITIVE LOGITS

 confess

3.28

 confessed

3.14

 confession

3.05

 confessions

2.80

 repent

1.38

 profess

1.30

 repentance

1.23

 incrim

1.15

 contr

1.15

 admitting

1.13

Activations Density 0.031%

phrases related to disclosure of personal information

references to confessions or acts of admitting wrongdoing

No Comments

No Known Activations