INDEX

Explanations

terms related to news events involving political figures and government officials

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nik

-0.32

agers

-0.29

killer

-0.28

bly

-0.28

 continuation

-0.28

attribute

-0.28

mil

-0.27

matic

-0.27

wolves

-0.27

 indu

-0.27

POSITIVE LOGITS

 Aires

0.34

 Cannes

0.34

 Lumpur

0.32

 Cologne

0.31

RTX

0.30

 Zurich

0.30

 Portsmouth

0.30

 Hogwarts

0.29

âĶĢâĶĢâĶĢâĶĢ

0.29

 Sector

0.29

Activations Density 6.727%

terms related to news events involving political figures and government officials

No Comments

No Known Activations