INDEX

Explanations

instances of contrasting information or exceptions in a narrative

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

aths

-0.29

 anthem

-0.28

ãĤĮ

-0.28

 segment

-0.27

guard

-0.27

 morning

-0.26

onomy

-0.26

ãģ®

-0.26

 Rolls

-0.26

hall

-0.26

POSITIVE LOGITS

tons

0.50

 alas

0.49

chery

0.39

tery

0.38

 nevertheless

0.38

etheless

0.37

 interestingly

0.35

uin

0.35

 nonetheless

0.35

 beware

0.35

Activations Density 4.436%

instances of contrasting information or exceptions in a narrative

No Comments

No Known Activations