INDEX

Explanations

statements related to mathematical results and theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

tagHelperRunner

-0.80



-0.78

 الرياضيه

-0.73

WriteBarrier

-0.71

 beginnetje

-0.68

 recommandée

-0.66

 Wikimedijinoj

-0.64

RegistryLite

-0.63

Хьажоргаш

-0.63

IContainer

-0.63

POSITIVE LOGITS

 theorem

0.84

 Theorem

0.74

Theorem

0.73

 theorems

0.72

theorem

0.62

 THEOREM

0.60

 proof

0.60

 statement

0.59

 resultado

0.59

 affirm

0.58

Activations Density 1.585%

statements related to mathematical results and theorems

No Comments

No Known Activations