INDEX

Explanations

mathematical terminology and notation related to sets, functions, and algebraic structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

‍

-0.49

 effectively

-0.48

 realised

-0.48

 незавершена

-0.46

 variation

-0.44

 Effectively

-0.44

 quem

-0.44

 της

-0.43

 consigue

-0.43

Facades

-0.43

POSITIVE LOGITS

Халык

0.64

 Мексичка

0.62

MemoryWarning

0.62

HostException

0.61

Erreferentziak

0.60

unnitel

0.59

ništ

0.58

kuuta

0.58

IntoConstraints

0.56

 MainAxisSize

0.56

Activations Density 1.678%

mathematical terminology and notation related to sets, functions, and algebraic structures

No Comments

No Known Activations