INDEX

Explanations

descriptions or mentions of things that are pure

oai_token-act-pair · gpt-3.5-turbo

instances of the word "pure" and its various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

apter

-0.85

 prominently

-0.73

 closest

-0.72

è¦ļéĨĴ

-0.72

 challeng

-0.72

 notor

-0.67

orrow

-0.66

 Peninsula

-0.66

ockets

-0.65

agements

-0.65

POSITIVE LOGITS

bred

1.23

waters

1.00

blood

0.95

0.84

st

0.81

blooded

0.80

water

0.78

pure

0.76

hide

0.76

ified

0.73

Activations Density 0.021%

descriptions or mentions of things that are pure

instances of the word "pure" and its various contexts

No Comments

No Known Activations