INDEX

Explanations

technical jargon related to algorithms and systems architecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Auto

-0.50

Auto

-0.45

No

-0.45

 auto

-0.43

 кӀ

-0.42

sigt

-0.42

linge

-0.42

 Full

-0.41

 áll

-0.41

(())

-0.41

POSITIVE LOGITS

 Separate

1.21

 separate

1.20

Separate

1.16

 SEPAR

1.13

separate

1.10

 seperate

1.07

 separado

0.99

 separates

0.98

 Separ

0.97

 separating

0.94

Activations Density 0.908%

technical jargon related to algorithms and systems architecture

No Comments

No Known Activations