INDEX

Explanations

references to specific measurements and parameters in experimental data

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

Mathematical/chemical formulas and symbols

np_acts-logits-general · gemini-2.0-flash

volume greater than size

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.47

Dom

-0.43

pela

-0.40

The

-0.40

-0.39

 фа

-0.38

te

-0.38

هم

-0.38

енный

-0.37

 side

-0.37

POSITIVE LOGITS

 nahilalakip

1.13

 disambiguazione

1.05

dafx

1.04

 AssemblyProduct

1.03

UnitTesting

0.99

WithIOException

0.97

StoreMessageInfo

0.95

verwijspagina

0.95

 propOrder

0.94

principalTable

0.91

Activations Density 0.937%

references to specific measurements and parameters in experimental data

Mathematical/chemical formulas and symbols

volume greater than size

No Comments

No Known Activations