INDEX

Explanations

mentions of the CIA

oai_token-act-pair · gpt-3.5-turbo

references to the CIA

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mulcair

-0.74

kj

-0.72

inances

-0.69

igans

-0.69

own

-0.68

lang

-0.68

alist

-0.67

 Leafs

-0.67

ths

-0.67

cies

-0.67

POSITIVE LOGITS

 annex

0.87

 Director

0.83

 operatives

0.77

CIA

0.76

 operative

0.75

CIA

0.75

 Headquarters

0.73

 covert

0.72

 assassinate

0.71

 counterterrorism

0.71

Activations Density 0.019%

mentions of the CIA

references to the CIA

No Comments

No Known Activations