INDEX

Explanations

a variety of medical terms related to diseases and treatments, particularly focusing on cancer cells and immune system-related terms

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

hift

-0.51

laus

-0.49

chwitz

-0.47

posts

-0.46

ammy

-0.45

CRIP

-0.44

dated

-0.43

¿½

-0.43

lift

-0.43

osher

-0.42

POSITIVE LOGITS

ular

0.70

ency

0.49

icidal

0.49

ularity

0.47

 biologist

0.45

 Biology

0.44

 Apocalypse

0.44

 Friendly

0.44

asc

0.43

estial

0.43

Activations Density 8.368%

a variety of medical terms related to diseases and treatments, particularly focusing on cancer cells and immune system-related terms

No Comments

No Known Activations