INDEX

Explanations

URLs

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

 Lauder

-0.68

 passports

-0.64

soDeliveryDate

-0.63

lings

-0.60

oyer

-0.60

 ambul

-0.59

onse

-0.59

cliffe

-0.59

BILITIES

-0.58

urion

-0.56

POSITIVE LOGITS

 documenting

0.72

ventures

0.63

 exposing

0.61

sylv

0.60

userc

0.59

ndra

0.59

 spew

0.59

rint

0.59

 Wheat

0.58

](

0.58

Activations Density 12.354%

URLs

No Comments

No Known Activations