INDEX

Explanations

references to legal or bureaucratic processes

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

 Municip

-0.83

swer

-0.82

 planners

-0.80

 istg

-0.79

ammers

-0.79

 envy

-0.77

Thumbnail

-0.75

 Fram

-0.74

tarians

-0.72

apist

-0.71

POSITIVE LOGITS

 consecutive

1.09

 aspects

1.05

 dozen

1.03

ones

1.01

 kinds

1.00

things

0.98

thin

0.96

THING

0.94

 instances

0.92

 additional

0.90

Activations Density 4.153%

references to legal or bureaucratic processes

No Comments

No Known Activations