INDEX

Explanations

references to technical terms or specialized jargon, particularly from formal sources or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 lenker

-1.15

 مشين

-1.05

 nahilalakip

-1.02

 autorytatywna

-0.99

Autoritní

-0.98

SourceChecksum

-0.96

 ExecuteAsync

-0.96

featureID

-0.96

 typelib

-0.96

IsContent

-0.96

POSITIVE LOGITS

 EdgeInsets

3.70

EdgeInsets

1.04

FromArgb

0.61

 FetchType

0.57

DotNetBar

0.55

0.52

 BorderRadius

0.51

Insets

0.49

 felt

0.48

beforeSend

0.47

Activations Density 0.011%

references to technical terms or specialized jargon, particularly from formal sources or publications

No Comments

No Known Activations