INDEX

Explanations

phrases related to misinformation or deception

oai_token-act-pair · gpt-3.5-turbo

instances of the word "misleading" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mun

-0.71

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.68

riot

-0.67

itar

-0.66

aldo

-0.65

ucha

-0.63

area

-0.62

mega

-0.62

ube

-0.59

cakes

-0.59

POSITIVE LOGITS

ingly

1.01

 misleading

0.83

 misled

0.80

sters

0.79

 deceive

0.78

 mislead

0.78

fully

0.75

ulence

0.71

 Disclosure

0.69

ulent

0.69

Activations Density 0.026%

phrases related to misinformation or deception

instances of the word "misleading" and its variants

No Comments

No Known Activations