INDEX

Explanations

Bullets or list items with specific properties like start or end symbols

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics related to various topics

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

 enthusi

-0.70

achev

-0.69

 Ukrain

-0.68

hement

-0.68

ury

-0.67

gans

-0.64

 Haku

-0.64

uca

-0.62

 encount

-0.61

ttes

-0.61

POSITIVE LOGITS

RAW

1.47

Loading

1.32

rawdownloadcloneembedreportprint

1.00

Posted

0.98

Reviewer

0.84

posted

0.84

«ĺ

0.83

CRE

0.80

actionDate

0.80

Topic

0.80

Activations Density 0.321%

Bullets or list items with specific properties like start or end symbols

numerical data or statistics related to various topics

No Comments

No Known Activations