INDEX

Explanations

elements indicating proofs or propositions in mathematical texts

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

出版年

-0.78

########.

-0.76

 SEDS

-0.76

URLException

-0.75

findpost

-0.67

Personendaten

-0.63

 Roskov

-0.63

raisemb

-0.62

帖最后由

-0.62

+#+#

-0.62

POSITIVE LOGITS

Proof

0.90

 Proof

0.85

 proof

0.82

proof

0.78

PROOF

0.68

 Theorem

0.64

Definition

0.62

remark

0.61

 Corollary

0.60

 PROOF

0.59

Activations Density 0.980%

elements indicating proofs or propositions in mathematical texts

No Comments

No Known Activations