INDEX

Explanations

the presence of specific symbols or formatting elements commonly found in programming or data notation

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

before capitalized words

np_acts-logits-general · gemini-2.0-flash

access controller or method

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 же

-0.49

 وتسجيلات

-0.46

ker

-0.44

ально

-0.44

UIKit

-0.44

TOBER

-0.43

وحة

-0.42

avit

-0.41

 tredje

-0.40

ula

-0.40

POSITIVE LOGITS

 AssemblyCompany

1.03

 referenties

0.97

migrationBuilder

0.94

IntoConstraints

0.90

 يتيمه

0.90

 MainAxisSize

0.89

rungsseite

0.89

 متعلقه

0.87

 فريبيس

0.86

 Lightboxes

0.86

Activations Density 0.493%

the presence of specific symbols or formatting elements commonly found in programming or data notation

before capitalized words

access controller or method

No Comments

No Known Activations