INDEX

Explanations

terms related to misleading or deceptive information

oai_token-act-pair · gpt-3.5-turbo

terms related to deception or misleading information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

riot

-0.78

hens

-0.76

oleon

-0.74

ateur

-0.73

mega

-0.72

mun

-0.72

foreseen

-0.71

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.71

area

-0.68

aldo

-0.67

POSITIVE LOGITS

 misleading

0.89

 statements

0.85

 disclosures

0.84

 misrepresent

0.83

 misled

0.83

ingly

0.80

 deceive

0.79

 omission

0.78

 mislead

0.77

 falsely

0.76

Activations Density 0.050%

terms related to misleading or deceptive information

terms related to deception or misleading information

No Comments

No Known Activations