INDEX

Explanations

dates within specific contexts

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

ividual

-0.88

inburgh

-0.78

AFTA

-0.73

ktop

-0.65

cellence

-0.62

oreal

-0.62

 practise

-0.61

ffield

-0.60

undai

-0.60

 territ

-0.60

POSITIVE LOGITS

Merc

0.66

Credit

0.61

Contact

0.58

jc

0.58

Loc

0.58

":"/

0.57

Recommend

0.56

jas

0.56

photos

0.55

jj

0.55

Activations Density 0.007%

dates within specific contexts

No Comments

No Known Activations