INDEX

Explanations

terms related to historical events and figures

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

ording

-1.01

assic

-0.99

adium

-0.98

assian

-0.95

frame

-0.94

icultural

-0.91

redit

-0.90

vasive

-0.90

itation

-0.88

aimon

-0.88

POSITIVE LOGITS

¬

1.34

vre

1.29

·

1.24

lette

1.18

rics

1.11

tis

1.08

1.04

ħ

1.04

Â¯Â¯Â¯Â¯

1.03

¸

1.02

Activations Density 0.707%

terms related to historical events and figures

No Comments

No Known Activations