INDEX

Explanations

technical terms related to protocols and standards

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

 Ramirez

-0.12

PF

-0.12

 Claire

-0.12

 Martinez

-0.12

za

-0.12

METHOD

-0.12

pas

-0.11

 Barkley

-0.11

 Elys

-0.11

ORPG

-0.11

POSITIVE LOGITS

idel

0.13

 naked

0.13

aming

0.12

iger

0.11

 clothed

0.11

etting

0.11

ebus

0.11

ATA

0.11

RFC

0.11

idal

0.11

Activations Density 17.414%

technical terms related to protocols and standards

No Comments

No Known Activations