INDEX

Explanations

specific words associated with governmental or political documents and communication, specifically focusing on the word "memo."

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

-0.79

sv

-0.70

untu

-0.70

ship

-0.68

Vik

-0.65

Fen

-0.64

icators

-0.62

½

-0.62

Alien

-0.60

hips

-0.60

POSITIVE LOGITS

ovie

1.06

andum

1.06

iere

0.86

pora

0.86

ieri

0.85

osal

0.85

ufact

0.80

ographed

0.80

arios

0.79

 memo

0.78

Activations Density 6.287%

specific words associated with governmental or political documents and communication, specifically focusing on the word "memo."

No Comments

No Known Activations