INDEX

Explanations

numerical measurements and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 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

featureID

-0.67

cydow

-0.60

 enfans

-0.59

 feroit

-0.55

 fédé

-0.53

 miniaturka

-0.52

 împre

-0.52

 onPostExecute

-0.52

 étan

-0.51

endmodule

-0.50

POSITIVE LOGITS

 ujednoznacz

0.39

ruik

0.37

FIT

0.36

gilan

0.35

In

0.35

Bra

0.35

 SAFE

0.35

 damaging

0.35

 Snell

0.35

Activations Density 1.728%

numerical measurements and their relationships

No Comments

No Known Activations