INDEX

Explanations

dates and locations in news articles

oai_token-act-pair · gpt-3.5-turbo

date and location references within text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 treaties

-0.52

 Romans

-0.52

wo

-0.51

 anat

-0.50

adium

-0.50

 unanswered

-0.49

 categ

-0.49

 mole

-0.48

 conc

-0.48

breeding

-0.48

POSITIVE LOGITS

0.99

0.88

0.87

0.84

0.78

0.77

0.76

0.74

interstitial

0.74

Activations Density 0.033%

dates and locations in news articles

date and location references within text

No Comments

No Known Activations