INDEX

Explanations

concepts related to policy-making and strategic decision-making in various contexts

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

Negative Logits

ITNESS

-0.90

 Stain

-0.88

Ago

-0.85

Gaw

-0.81

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.80

ymes

-0.79

hma

-0.78

lihood

-0.78

 Templ

-0.78

upon

-0.76

POSITIVE LOGITS

 makers

1.17

 prescriptions

1.14

making

1.14

 policy

1.13

policy

1.04

 stance

1.03

makers

1.03

 formulation

1.03

 escalation

1.01

 advisors

1.01

Activations Density 5.660%

concepts related to policy-making and strategic decision-making in various contexts

No Known Activations