INDEX

Explanations

formal statements and results in mathematical or statistical theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

gdx

-0.57

 findViewById

-0.56

ękuję

-0.56

CodedInputStream

-0.55

Viited

-0.55

 Sovi

-0.54

 vibra

-0.53

 risers

-0.52

 ſever

-0.52

 cland

-0.52

POSITIVE LOGITS

MemoryWarning

0.82

पया

0.77

 theorem

0.66

Theorem

0.62

NgModule

0.60

 Theorem

0.56

ModelState

0.54

stateProvider

0.54

 élevées

0.54

::~

0.52

Activations Density 0.684%

formal statements and results in mathematical or statistical theorems

No Comments

No Known Activations