INDEX

Explanations

words related to medical conditions and treatments, including drug names and physical procedures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BIL

-1.09

éĹĺ

-0.96

GBT

-0.88

ELY

-0.87

 Progressive

-0.86

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

-0.84

 fitting

-0.84

ãģ®éŃĶ

-0.84

eers

-0.83

kus

-0.83

POSITIVE LOGITS

osate

1.94

antom

1.74

osph

1.68

ysics

1.67

tml

1.42

obia

1.41

inx

1.38

onso

1.36

ttp

1.33

ysical

1.33

Activations Density 3.914%

words related to medical conditions and treatments, including drug names and physical procedures

No Comments

No Known Activations