INDEX

Explanations

references to heavy metals, specifically lead

oai_token-act-pair · gpt-3.5-turbo

references to lead and its associated risks and impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

NEY

-0.79

 Fant

-0.77

 Wanted

-0.77

fare

-0.73

 Kard

-0.72

 Favor

-0.71

NCT

-0.70

 Grande

-0.70

ctors

-0.68

 Tanz

-0.68

POSITIVE LOGITS

 oxide

1.26

 poisoning

1.09

 neurot

1.08

 arsenic

1.06

 chloride

1.04

nit

1.01

 toxicity

1.01

 alloy

1.01

 contaminants

0.99

 sulf

0.98

Activations Density 0.031%

references to heavy metals, specifically lead

references to lead and its associated risks and impacts

No Comments

No Known Activations