INDEX

Explanations

personal experiences and reflections shared in a narrative form

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

States

-0.66

rouse

-0.63

oses

-0.61

apo

-0.59

istically

-0.59

ifles

-0.58

idental

-0.57

erning

-0.55

warts

-0.54

ierrez

-0.54

POSITIVE LOGITS

ĸļ

0.73

 awhile

0.67

 downhill

0.61

 proven

0.60

 since

0.58

 Gone

0.56

cffffcc

0.55

 plenty

0.55

 awfully

0.54

ī

0.54

Activations Density 12.516%

personal experiences and reflections shared in a narrative form

No Comments

No Known Activations