INDEX

Explanations

keywords related to medical conditions and procedural language

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

Code-related vocabulary

np_acts-logits-general · gemini-2.0-flash

decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

 Normdatei

-0.62

 OFDb

-0.61

ríamos

-0.56

 الرخصة

-0.54

RunWith

-0.54

 nahilalakip

-0.52

}{@

-0.51

 архивлан

-0.51

multicolumn

-0.50

(_,

-0.50

POSITIVE LOGITS

0.56

 confronti

0.52

ŝ

0.51

 ankaŭ

0.51

aŭ

0.50

igata

0.48

0.47

 ligiloj

0.46

 spalle

0.46

Activations Density 0.033%

keywords related to medical conditions and procedural language

Code-related vocabulary

decision-making

No Comments

No Known Activations