INDEX

Explanations

mathematical terms and concepts related to proof construction

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

hdashline

-0.59

出版年

-0.57

AddHtmlAttribute

-0.55

Üdv

-0.53

 lèvres

-0.49

ruptedException

-0.49

endforeach

-0.48

équation

-0.48

styleable

-0.47

الإنجليزية

-0.47

POSITIVE LOGITS

 proof

0.91

 proofs

0.78

 proving

0.75

proof

0.73

Proof

0.71

 PROOF

0.70

TagMode

0.70

PROOF

0.69

 Proof

0.69

 induction

0.69

Activations Density 1.324%

mathematical terms and concepts related to proof construction

No Comments

No Known Activations