INDEX

Explanations

repeated mentions of the term "order" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

edicated

-0.59

rapnel

-0.57

énus

-0.56

etheless

-0.56

eniably

-0.53

/#{

-0.53

`;

-0.52

 useNavigate

-0.52

ceuticals

-0.51

 downvoted

-0.51

POSITIVE LOGITS

 order

4.77

 Order

4.41

 ORDER

4.05

order

4.04

Order

4.02

 orders

3.90

ORDER

3.54

 Orders

3.54

 ordering

3.20

orders

3.19

Activations Density 0.099%

repeated mentions of the term "order" in various contexts

No Comments

No Known Activations