INDEX

Explanations

information related to legal cases or government actions with some negative 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

uci

-0.56

igmatic

-0.56

angu

-0.54

sburg

-0.53

agall

-0.51

iors

-0.50

grain

-0.49

 Deity

-0.49

Switch

-0.49

paren

-0.48

POSITIVE LOGITS

 however

0.85

 billed

0.65

 dubbed

0.65

 moreover

0.64

 namely

0.62

 comprising

0.62

 incidentally

0.60

 according

0.59

 albeit

0.59

 titled

0.59

Activations Density 19.332%

information related to legal cases or government actions with some negative context

No Comments

No Known Activations