INDEX

Explanations

names of hockey teams

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

tons

-0.68

é¾įåĸļå£«

-0.64

ername

-0.63

phone

-0.59

colo

-0.57

plot

-0.56

 Fighter

-0.56

farm

-0.56

friend

-0.56

office

-0.55

POSITIVE LOGITS

 Oilers

1.01

monton

0.72

eger

0.69

Kings

0.66

gom

0.65

Esk

0.63

âĹ¼

0.61

itious

0.60

phies

0.58

uating

0.57

Activations Density 7.310%

names of hockey teams

No Comments

No Known Activations