INDEX

Explanations

occurrences of the word "gate."

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

hovah

-0.47

ľ

-0.44

inary

-0.43

uania

-0.42

urgy

-0.41

acebook

-0.40

anian

-0.40

ogun

-0.40

uitive

-0.39

 Adin

-0.39

POSITIVE LOGITS

way

0.56

boro

0.49

gate

0.48

agher

0.47

 Papers

0.46

eln

0.46

forth

0.45

leaf

0.45

plot

0.44

WAY

0.43

Activations Density 11.276%

occurrences of the word "gate."

No Comments

No Known Activations