INDEX

Explanations

sentences discussing conditions or errors in a technical or system context

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

Error messages or warnings across languages

np_acts-logits-general · gemini-2.0-flash

foreign language system errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 autorytatywna

-0.86

 ***!

-0.69

 EconPapers

-0.65

DriverManager

-0.63

ItemBackground

-0.60

 snippetHide

-0.59

Rüyada

-0.59

 onPostExecute

-0.58

esgue

-0.58

//</

-0.57

POSITIVE LOGITS

MigrationBuilder

0.56

 XCTest

0.50

udar

0.44

ombres

0.43

modelBuilder

0.42

Errorf

0.42

 threat

0.42

 Incident

0.42

 Slight

0.42

depre

0.41

Activations Density 0.035%

sentences discussing conditions or errors in a technical or system context

Error messages or warnings across languages

foreign language system errors

No Comments

No Known Activations