INDEX

Explanations

references to data or statistical analyses

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

</strong>

-0.50

Према

-0.48

NullException

-0.46

 Decker

-0.46

”

-0.46

,”

-0.45

 становника

-0.44

 Kommune

-0.44

grà

-0.44

日発売

-0.43

POSITIVE LOGITS

onViewCreated

0.64

بوابة

0.62

 Cili

0.62

jooq

0.61

󠁴

0.59

 Sandro

0.58

 EconPapers

0.58

 edits

0.58

roek

0.57

 scaff

0.57

Activations Density 0.059%

references to data or statistical analyses

No Comments

No Known Activations