INDEX

Explanations

mathematical symbols and related text

oai_token-act-pair · gpt-3.5-turbo

phrases related to negative consequences or effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 guiActiveUnfocused

-0.73

Tid

-0.70

 scatter

-0.66

 Dirt

-0.63

 Libyan

-0.61

FAR

-0.60

 Golem

-0.59

FAT

-0.59

 Belg

-0.57

 subur

-0.57

POSITIVE LOGITS

should

0.87

¹

0.85

-|

0.84

Â¢

0.83

could

0.83

Â§

0.79

£

0.79

catentry

0.78

âĢķ

0.78

there

0.78

Activations Density 0.575%

mathematical symbols and related text

phrases related to negative consequences or effects

No Comments

No Known Activations