INDEX

Explanations

phrases related to deception and misinformation

oai_token-act-pair · gpt-3.5-turbo

concepts related to misinformation and deception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ahime

-0.93

ktop

-0.80

inement

-0.79

limits

-0.76

adelphia

-0.73

unctions

-0.73

uve

-0.72

phabet

-0.72

 Ports

-0.71

POSITIVE LOGITS

 fake

2.05

 hoax

1.98

 Fake

1.93

 faked

1.88

 phony

1.86

Fake

1.86

 false

1.85

 falsehood

1.84

 deception

1.82

 bogus

1.78

Activations Density 0.614%

phrases related to deception and misinformation

concepts related to misinformation and deception

No Comments

No Known Activations