INDEX

Explanations

references to variables and symbols typically used in programming or mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

soort

-0.73

*/

-0.70

IsPostBack

-0.66

AddAttribute

-0.66

</i>

-0.64

 defaultdict

-0.63

'>"

-0.62

 ProgressDialog

-0.62

rcParams

-0.62

aarrggbb

-0.62

POSITIVE LOGITS

 getX

1.34

getX

1.32

 Xanth

1.28

1.26

 xanth

1.20

 Xavier

1.20

 Xander

1.17

1.14

1.13

Xy

1.11

Activations Density 0.676%

references to variables and symbols typically used in programming or mathematical contexts

No Comments

No Known Activations