INDEX

Explanations

comparative phrases indicating relationships or differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

();)

-0.45

 aldea

-0.44

iyor

-0.43

jno

-0.43

 seme

-0.43

maine

-0.42

 snare

-0.42

 Rusi

-0.41

won

-0.41

 pasti

-0.41

POSITIVE LOGITS

IVEREF

0.76

 demais

0.74

AndEndTag

0.73

ValueGeneration

0.69

 other

0.69

 AssemblyCompany

0.68

IContainer

0.64

Jereo

0.64

contentLoaded

0.63

 StatelessWidget

0.63

Activations Density 0.370%

comparative phrases indicating relationships or differences

No Comments

No Known Activations