INDEX

Explanations

technical terms and concepts related to experimentation and software development

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

andra

-0.61

pered

-0.58

veland

-0.57

atra

-0.56

adr

-0.55

kins

-0.55

cript

-0.54

holders

-0.54

utra

-0.54

ETS

-0.54

POSITIVE LOGITS

imental

0.67

ists

0.64

 treatments

0.55

 Prototype

0.54

arm

0.54

oad

0.52

ized

0.51

 explor

0.51

 treatment

0.50

 aspects

0.50

Activations Density 8.194%

technical terms and concepts related to experimentation and software development

No Comments

No Known Activations