INDEX

Explanations

terms related to security and law enforcement

oai_token-act-pair · gpt-3.5-turbo

terms related to security and safety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

oric

-0.83

igible

-0.81

omorphic

-0.73

sembly

-0.70

thritis

-0.68

cipled

-0.68

yss

-0.67

 Invention

-0.67

heit

-0.67

ufact

-0.66

POSITIVE LOGITS

 checkpoints

1.11

 guards

1.09

 clearance

1.02

 personnel

0.99

 guard

0.95

 checkpoint

0.91

 breaches

0.90

 forces

0.90

 precautions

0.89

 screenings

0.88

Activations Density 0.045%

terms related to security and law enforcement

terms related to security and safety

No Comments

No Known Activations