INDEX

Explanations

numerical values with high activation

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistics related to various entities or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

DragonMagazine

-0.83

Reviewer

-0.81

Thumbnail

-0.71

ocobo

-0.70

çīĪ

-0.65

ilant

-0.64

 fide

-0.63

ãĥ´ãĤ¡

-0.63

channelAvailability

-0.63

plot

-0.62

POSITIVE LOGITS

 lashes

0.61

Rs

0.60

 Martial

0.57

 martial

0.57

 berth

0.56

Ala

0.56

0.55

 caste

0.55

Activations Density 0.102%

numerical values with high activation

numerical data and statistics related to various entities or subjects

No Comments

No Known Activations