INDEX

Explanations

phrases related to the role or influence of various entities in different contexts

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

ifted

-0.59

imb

-0.55

ornia

-0.54

orrect

-0.50

lad

-0.49

ageddon

-0.49

worthy

-0.48

icon

-0.48

cember

-0.47

pora

-0.46

POSITIVE LOGITS

wright

0.81

ername

0.68

wr

0.65

 Played

0.60

 played

0.60

ulative

0.60

 havoc

0.59

 Piano

0.59

rored

0.57

natureconservancy

0.57

Activations Density 9.447%

phrases related to the role or influence of various entities in different contexts

No Comments

No Known Activations