INDEX

Explanations

repeated occurrences or mentions of a particular topic or event

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

aceous

-1.27

Reviewer

-1.21

Marginal

-1.10

XT

-1.07

agra

-1.07

ourt

-1.00

rats

-1.00

uld

-1.00

iar

-0.99

oola

-0.97

POSITIVE LOGITS

 consecut

1.22

cale

1.14

 throughout

1.05

fold

1.03

coded

1.03

 cited

0.95

points

0.91

soever

0.89

manship

0.88

poons

0.88

Activations Density 1.077%

repeated occurrences or mentions of a particular topic or event

No Comments

No Known Activations