INDEX

Explanations

references to the term "Raw" with various intensities

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

 Explain

-1.13

uate

-1.11

ippi

-1.04

itism

-1.02

OPA

-0.99

onial

-0.98

arios

-0.98

ossession

-0.97

UNCH

-0.97

ŃĶ

-0.96

POSITIVE LOGITS

hide

1.71

ls

1.45

lings

1.39

lins

1.31

esome

1.28

 sewage

1.25

 throats

1.14

raw

1.08

 materials

1.06

blood

1.01

Activations Density 0.787%

references to the term "Raw" with various intensities

No Comments

No Known Activations