INDEX

Explanations

conversations and dialogues within a structured context

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

tics

-0.28

laws

-0.25

anmar

-0.25

 somew

-0.24

abad

-0.24

toc

-0.24

tips

-0.23

 surn

-0.23

PDATE

-0.23

visible

-0.23

POSITIVE LOGITS

rien

0.29

âĢĳ

0.27

 gentleman

0.26

rick

0.25

Chuck

0.24

 Speaker

0.24

 Russ

0.24

ItemImage

0.24

Repeat

0.24

 Robb

0.24

Activations Density 7.581%

conversations and dialogues within a structured context

No Comments

No Known Activations