INDEX

Explanations

technical terms and structure related to coding or documentation

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

tonode

-0.43

 Donald

-0.42

 CURLOPT

-0.38

gnet

-0.37

TemporalType

-0.36

襄

-0.36

 Reden

-0.36

 steamed

-0.35

দের

-0.35

Butyl

-0.35

POSITIVE LOGITS

Билгалдахарш

1.03

دانشنامهٔ

0.85

ViewImports

0.81

richTextPanel

0.79

 للمعارف

0.71

AccessorTable

0.69

Geplaatst

0.69

سطس

0.69

 дописавши

0.69

Tembelea

0.69

Activations Density 2.038%

technical terms and structure related to coding or documentation

No Comments

No Known Activations