INDEX

Explanations

mentions of specific sections or recommendations within a publication

oai_token-act-pair · gpt-3.5-turbo

the term "Picks" in various contexts related to selections or recommendations

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

 stret

-0.75

lia

-0.69

gren

-0.68

flying

-0.66

gal

-0.66

igi

-0.64

 appar

-0.63

stood

-0.62

acion

-0.61

steam

-0.60

POSITIVE LOGITS

 Picks

1.29

yright

0.71

ļéĨĴ

0.71

ettings

0.71

-+-+

0.66

 Deadly

0.66

 Received

0.65

 Important

0.64

 Reached

0.64

ensical

0.63

Activations Density 0.009%

mentions of specific sections or recommendations within a publication

the term "Picks" in various contexts related to selections or recommendations

No Comments

No Known Activations