INDEX

Explanations

references to the CIA

oai_token-act-pair · gpt-3.5-turbo

mentions of the CIA and related personnel

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

kj

-0.73

 Mulcair

-0.72

own

-0.70

igans

-0.70

ghai

-0.70

ths

-0.70

inances

-0.70

 Leafs

-0.68

 QuÃ©

-0.67

ï¸

-0.67

POSITIVE LOGITS

 annex

0.95

 Director

0.84

CIA

0.82

 operative

0.81

 operatives

0.79

 Headquarters

0.78

 covert

0.75

CIA

0.75

 counterterrorism

0.74

 headquarters

0.74

Activations Density 0.021%

references to the CIA

mentions of the CIA and related personnel

No Comments

No Known Activations