INDEX

Explanations

mentions of legal processes and criminal activities

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

 apes

-0.65

 metic

-0.64

 flowering

-0.63

 primates

-0.63

 mounts

-0.63

 ancest

-0.63

 perspect

-0.62

 tabl

-0.60

 squirrel

-0.59

 Patriarch

-0.59

POSITIVE LOGITS

ï¸ı

0.91

ever

0.87

reci

0.82

null

0.81

âĵĺ

0.78

lean

0.78

Stra

0.77

----------------------------------------------------------------

0.77

VICE

0.76

\-

0.76

Activations Density 5.113%

mentions of legal processes and criminal activities

No Comments

No Known Activations