INDEX

Explanations

Twitter handles or usernames

oai_token-act-pair · gpt-3.5-turbo

specific alphanumeric identifiers or codes

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

conservancy

-0.74

 ingred

-0.73

 differe

-0.71

etheless

-0.70

 mathemat

-0.68

 nodd

-0.67

 suits

-0.63

 proble

-0.62

 arrang

-0.61

 trave

-0.61

POSITIVE LOGITS

—

1.26

pic

1.05

pic

0.98

0.86

0.82

Jr

0.82

0.80

0.79

--

0.78

0.77

Activations Density 0.022%

Twitter handles or usernames

specific alphanumeric identifiers or codes

No Comments

No Known Activations