INDEX

Explanations

physical actions or events described in technical detail

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

fter

-0.76

toggle

-0.72

picture

-0.68

][/

-0.65

guide

-0.62

anton

-0.59

ggles

-0.57

wine

-0.56

clip

-0.56

ADVERTISEMENT

-0.56

POSITIVE LOGITS

 raining

0.97

 predecessor

0.61

 costs

0.59

 impossible

0.59

 itself

0.58

rodu

0.58

 reopened

0.57

ãĥķãĤ©

0.57

 ratified

0.57

 cheaper

0.56

Activations Density 16.913%

physical actions or events described in technical detail

No Comments

No Known Activations