INDEX

Explanations

mathematical expressions and notations involving variables, operators, and constructs related to 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

 verdient

-0.54

Portail

-0.53

>),

-0.49

 сезоне

-0.47

gya

-0.46

 alle

-0.46

重的

-0.45

 batang

-0.45

miec

-0.45

rasti

-0.44

POSITIVE LOGITS

AnchorStyles

0.85

 Audiodateien

0.84

 GenerationType

0.79

Datuak

0.79

 Référence

0.78

 getItemId

0.78

 zirc

0.74

InvalidProtocol

0.71

 OnTrigger

0.71

ContentLoaded

0.70

Activations Density 0.812%

mathematical expressions and notations involving variables, operators, and constructs related to equations

No Comments

No Known Activations