INDEX

Explanations

references to specific research contributions and methods

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

References with bracketed metadata

np_acts-logits-general · gemini-2.0-flash

academic proceedings titles

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

instancetype

-0.50

 mass

-0.47

солю

-0.45

cjon

-0.45

 uska

-0.45

dious

-0.44

cjs

-0.44

weder

-0.43

 Tapatalk

-0.43

.[/

-0.42

POSITIVE LOGITS

 IEEE

0.90

Datuak

0.76

tagHelperRunner

0.74

IEEE

0.72

 Computing

0.67

 mergeFrom

0.67

 computing

0.66

 epileptic

0.65

 calyx

0.63

 arquitect

0.63

Activations Density 2.657%

references to specific research contributions and methods

References with bracketed metadata

academic proceedings titles

No Comments

No Known Activations