INDEX

Explanations

terms related to various types of pollution, including air pollution and noise pollution

oai_token-act-pair · gpt-3.5-turbo

references to environmental pollution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ndra

-0.82

llan

-0.73

igmat

-0.72

orian

-0.71

thood

-0.71

inosaur

-0.68

uscript

-0.68

strap

-0.68

uberty

-0.67

beit

-0.67

POSITIVE LOGITS

 pollution

1.10

 polluted

0.95

 contamin

0.95

 poisoning

0.93

 pollut

0.91

 pollutants

0.90

 spills

0.89

 fumes

0.87

 contaminants

0.84

 spew

0.83

Activations Density 0.055%

terms related to various types of pollution, including air pollution and noise pollution

references to environmental pollution

No Comments

No Known Activations