INDEX

Explanations

symbols and notation used in mathematical expressions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 later

-0.65

-0.64

-0.63

 Lora

-0.60

mathcal

-0.60

CA

-0.60

The

-0.56

kal

-0.55

Kol

-0.55

 cose

-0.54

POSITIVE LOGITS

ftagPool

0.91

:✨

0.87

UrlResolution

0.85

̈́

0.83

 utafitiHapana

0.83

 OGSÅ

0.80

 дописавши

0.76

posedge

0.76

ConstraintMaker

0.76

 فريبيس

0.75

Activations Density 0.353%

symbols and notation used in mathematical expressions and equations

No Comments

No Known Activations