INDEX

Explanations

mathematical concepts and terminology related to topology and group theory

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

Mathematical proofs or theorems

np_acts-logits-general · gemini-2.0-flash

mathematical proofs and theorems

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

during

-0.47

AddTagHelper

-0.45

Populate

-0.45

 during

-0.44

During

-0.43

 During

-0.41

 Vás

-0.41

McP

-0.40

 Across

-0.40

undheit

-0.40

POSITIVE LOGITS

 prove

0.78

 Prove

0.78

Prove

0.68

 irreducible

0.68

iff

0.68

 proof

0.67

 converse

0.67

 Proof

0.66

 isomorphism

0.66

 theorem

0.65

Activations Density 3.433%

mathematical concepts and terminology related to topology and group theory

Mathematical proofs or theorems

mathematical proofs and theorems

No Comments

No Known Activations