INDEX

Explanations

programming-related terms

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

quartered

-0.82

etheless

-0.80

ailability

-0.72

 accomp

-0.68

insula

-0.65

FORMATION

-0.60

tenance

-0.59

pressed

-0.59

 compr

-0.59

mercial

-0.59

POSITIVE LOGITS

Zer

0.75

ety

0.72

VA

0.70

Cast

0.68

Cry

0.68

yon

0.65

zeb

0.65

 Zion

0.65

?:

0.65

ember

0.64

Activations Density 21.781%

programming-related terms

No Comments

No Known Activations