INDEX

Explanations

mathematical notations and expressions associated with computational complexity and asymptotic analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 tube

-0.51

tube

-0.51

Tube

-0.46

 cold

-0.46

etre

-0.44

 Game

-0.43

نین

-0.42

ful

-0.42

 OMITBAD

-0.42

dae

-0.41

POSITIVE LOGITS

MigrationBuilder

0.96

awaiter

0.85

 EconPapers

0.83

Hozzáférés

0.79

KommentareTeilen

0.71

ConstraintMaker

0.70

AddTagHelper

0.69

featureID

0.69

WithIOException

0.67

PreferredItem

0.67

Activations Density 1.077%

mathematical notations and expressions associated with computational complexity and asymptotic analysis

No Comments

No Known Activations