INDEX

Explanations

arguments or discussions related to various topics, including scientific research, health policy, mathematical competence, and government actions

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

backer

-0.60

Guard

-0.60

PokÃ©

-0.56

aukee

-0.56

EMBER

-0.54

enge

-0.53

Baltimore

-0.53

ega

-0.52

Plus

-0.52

guard

-0.52

POSITIVE LOGITS

"[

0.60

 they

0.59

 someday

0.58

 although

0.57

cher

0.56

 there

0.56

 "âĢ¦

0.54

 whoever

0.53

 prevailed

0.53

 justifies

0.53

Activations Density 12.578%

arguments or discussions related to various topics, including scientific research, health policy, mathematical competence, and government actions

No Comments

No Known Activations