INDEX

Explanations

prepositions and prepositional phrases indicating location or direction

oai_token-act-pair · gpt-3.5-turbo

prepositions and spatial relations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Vaugh

-0.76

 thous

-0.64

 destro

-0.63

 corrid

-0.59

 Seym

-0.59

farious

-0.58

 blat

-0.57

 convol

-0.55

 disadvant

-0.55

jri

-0.54

POSITIVE LOGITS

 largeDownload

0.61

 PsyNet

0.51

 Overs

0.50

\":

0.50

ciples

0.48

OC

0.48

 OFFIC

0.47

FA

0.47

 NVIDIA

0.46

 ..........

0.46

Activations Density 1.038%

prepositions and prepositional phrases indicating location or direction

prepositions and spatial relations in the text

No Comments

No Known Activations