INDEX

Explanations

phrases related to legal and political discussions

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

aukee

-0.42

levard

-0.39

(.

-0.38

 Tanz

-0.37

cipl

-0.36

 comed

-0.36

inventoryQuantity

-0.35

ngth

-0.35

atican

-0.35

hov

-0.35

POSITIVE LOGITS

chard

0.46

past

0.45

other

0.42

odd

0.41

anos

0.41

DATA

0.40

anus

0.40

onian

0.39

nery

0.39

ALE

0.39

Activations Density 10.165%

phrases related to legal and political discussions

No Comments

No Known Activations