INDEX

Explanations

words related to deception or dishonesty

oai_token-act-pair · gpt-3.5-turbo

terms related to deception and dishonesty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

capacity

-0.83

foreseen

-0.78

 Mobility

-0.74

area

-0.74

radius

-0.69

rait

-0.69

trak

-0.69

served

-0.69

 Radius

-0.68

alg

-0.67

POSITIVE LOGITS

 misrepresent

1.18

 omission

1.15

 deceive

1.12

 deception

1.07

 falsely

1.07

 hoax

1.04

 obfusc

1.04

 deceived

1.03

 deceit

1.02

 liar

1.01

Activations Density 0.135%

words related to deception or dishonesty

terms related to deception and dishonesty

No Comments

No Known Activations