INDEX

Explanations

names of individuals or entities in a context that may involve conflicts, investigations, or changes in leadership

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

ategory

-0.62

orld

-0.60

yright

-0.58

orneys

-0.57

gettable

-0.56

riors

-0.56

feeding

-0.55

structed

-0.54

lear

-0.53

 parap

-0.53

POSITIVE LOGITS

Lud

0.63

ories

0.60

atures

0.58

wich

0.58

gets

0.57

azo

0.55

BuyableInstoreAndOnline

0.54

odan

0.54

lihood

0.54

entary

0.53

Activations Density 8.732%

names of individuals or entities in a context that may involve conflicts, investigations, or changes in leadership

No Comments

No Known Activations