INDEX

Explanations

phrases related to safety and security

oai_token-act-pair · gpt-3.5-turbo

references to safety in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

dx

-0.72

yi

-0.69

 Fiber

-0.68

ordan

-0.67

issance

-0.67

frey

-0.66

essee

-0.65

attr

-0.64

hour

-0.63

bender

-0.63

POSITIVE LOGITS

 safe

1.12

 Safe

0.89

safe

0.84

 havens

0.84

 evacuation

0.80

 safest

0.79

 safely

0.79

 safer

0.77

 Haram

0.76

saf

0.76

Activations Density 0.013%

phrases related to safety and security

references to safety in various contexts

No Comments

No Known Activations