INDEX

Explanations

situations or descriptions involving unpleasant physical sensations or conditions, such as stinging, foul odors, or physical discomfort

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

udeau

-0.59

sonian

-0.50

guided

-0.47

ational

-0.46

BOOK

-0.46

ilateral

-0.45

schild

-0.44

Broad

-0.44

PsyNetMessage

-0.44

ignment

-0.43

POSITIVE LOGITS

 fumes

0.73

 hatred

0.57

 thirst

0.56

 sore

0.56

 stains

0.54

 spew

0.53

 boiling

0.53

 waste

0.51

 poisonous

0.51

 agony

0.50

Activations Density 5.968%

situations or descriptions involving unpleasant physical sensations or conditions, such as stinging, foul odors, or physical discomfort

No Comments

No Known Activations