INDEX

Explanations

concepts related to environmental issues and pollution, particularly focusing on pollution in various contexts such as water pollution and air pollution

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

llan

-0.65

laus

-0.60

inosaur

-0.60

ndra

-0.59

Bone

-0.59

pha

-0.57

tre

-0.56

orian

-0.55

donald

-0.55

antine

-0.55

POSITIVE LOGITS

 pollution

0.77

 fumes

0.67

 pollutants

0.66

 pollut

0.64

 emissions

0.64

 polluted

0.62

ution

0.62

 contamin

0.62

 streams

0.60

 spew

0.60

Activations Density 7.188%

concepts related to environmental issues and pollution, particularly focusing on pollution in various contexts such as water pollution and air pollution

No Comments

No Known Activations