INDEX

Explanations

ways or methods of doing something, particularly in an organized or detailed manner

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

rament

-0.65

Dust

-0.65

 Patri

-0.63

tek

-0.61

 Wink

-0.58

ammy

-0.58

 Hansen

-0.58

hemat

-0.57

oning

-0.56

oppable

-0.56

POSITIVE LOGITS

isms

1.17

ality

0.83

 dictated

0.68

ism

0.68

othy

0.68

istic

0.67

alities

0.67

finding

0.66

istics

0.65

able

0.65

Activations Density 7.366%

ways or methods of doing something, particularly in an organized or detailed manner

No Comments

No Known Activations