INDEX

Explanations

proper nouns related to individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and significant titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

terday

-0.78

anwhile

-0.75

enegger

-0.73

ãĥ¼ãĥĨ

-0.68

ĸļ

-0.61

*/(

-0.61

ä

-0.61

etheless

-0.60

theless

-0.60

ÃĥÃĤ

-0.59

POSITIVE LOGITS

 Nebula

0.60

 River

0.59

iest

0.58

 Festival

0.57

 logo

0.56

 League

0.56

 Collective

0.56

 Centre

0.56

agame

0.56

 Registry

0.55

Activations Density 0.563%

proper nouns related to individuals or organizations

proper nouns, specifically names and significant titles

No Comments

No Known Activations