INDEX

Explanations

references to academic publications and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

<?

-0.51

Personendaten

-0.51

gro

-0.45

 verbally

-0.45

udsman

-0.43

Graphical

-0.43

Sko

-0.42

bson

-0.42

lich

-0.42

copy

-0.41

POSITIVE LOGITS

 lenker

0.80

 chapters

0.77

Proceedings

0.73

 PROCEEDINGS

0.73

 proceedings

0.73

Edited

0.72

chapter

0.72

 Fests

0.70

Handbook

0.70

 Proceedings

0.68

Activations Density 0.212%

references to academic publications and citations

No Comments

No Known Activations