INDEX

Explanations

words related to travel and specific details in a narrative context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

undai

-0.93

ogle

-0.92

cale

-0.87

glomer

-0.86

cium

-0.86

acebook

-0.85

uckland

-0.85

 mathemat

-0.83

avorite

-0.82

issance

-0.81

POSITIVE LOGITS

maker

1.10

makers

1.09

 makers

1.05

making

1.05

wise

1.04

goers

1.02

members

1.00

holders

0.99

kind

0.93

Maker

0.91

Activations Density 2.160%

words related to travel and specific details in a narrative context

No Comments

No Known Activations