INDEX

Explanations

numbers and technical terms

oai_token-act-pair · gpt-3.5-turbo

references to differences and comparisons in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 respectively

-0.80

Anyway

-0.58

 Chak

-0.56

etc

-0.56

 Kush

-0.56

 Jung

-0.54

Kiw

-0.53

 Optimus

-0.53

NZ

-0.52

 apiece

-0.52

POSITIVE LOGITS

âĢ

0.79

ãĤ¼ãĤ¦ãĤ¹

0.76

ãĢ

0.73

ãĥīãĥ©

0.64

advertisement

0.63

\",

0.63

ãĤ©

0.63

ãĥ´ãĤ¡

0.62

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.62

 âĢ

0.61

Activations Density 1.296%

numbers and technical terms

references to differences and comparisons in various contexts

No Comments

No Known Activations