INDEX

Explanations

commands or prompts starting with "Let's."

oai_token-act-pair · gpt-3.5-turbo

phrases or symbols that indicate commands or actions, particularly in the context of software interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

enegger

-0.84

 seiz

-0.71

 Annotations

-0.70

 lodging

-0.68

 Seym

-0.68

 mosqu

-0.66

 tremend

-0.65

çīĪ

-0.65

 horizont

-0.64

 transmitter

-0.64

POSITIVE LOGITS

ķ

0.89

ı

0.89

ĵ

0.86

º

0.84

Ľ

0.84

£

0.83

ulty

0.81

ongo

0.80

Ĵ

0.80

ĭ

0.78

Activations Density 0.080%

commands or prompts starting with "Let's."

phrases or symbols that indicate commands or actions, particularly in the context of software interaction

No Comments

No Known Activations