INDEX

Explanations

words related to safety

oai_token-act-pair · gpt-3.5-turbo

references to safety concerns and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

eric

-0.90

dx

-0.88

issance

-0.86

yss

-0.82

igs

-0.77

eta

-0.75

naire

-0.73

eds

-0.73

quart

-0.72

nant

-0.72

POSITIVE LOGITS

 safety

1.07

ailability

0.85

 valve

0.79

oided

0.78

safety

0.77

 practition

0.77

Þ

0.76

 precautions

0.75

 precaution

0.74

 hazards

0.72

Activations Density 0.021%

words related to safety

references to safety concerns and regulations

No Comments

No Known Activations