INDEX

Explanations

words related to lethal or dangerous situations

oai_token-act-pair · gpt-3.5-turbo

terms associated with lethal threats or serious harm

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

ourced

-0.90

erous

-0.86

ĸļ

-0.80

 Libraries

-0.78

mbuds

-0.78

adra

-0.77

ļéĨĴ

-0.76

unda

-0.76

ership

-0.76

estamp

-0.76

POSITIVE LOGITS

 poison

0.94

 poisonous

0.93

 dose

0.90

 wounding

0.89

 lethal

0.87

 overdose

0.86

 blow

0.85

 assault

0.84

 combination

0.84

 injection

0.84

Activations Density 0.022%

words related to lethal or dangerous situations

terms associated with lethal threats or serious harm

No Comments

No Known Activations