INDEX

Explanations

syntax and structure related to Java classes and methods

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

Mathematical expressions and special characters

np_acts-logits-general · gemini-2.0-flash

to replace

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.86

aarrggbb

-0.77

parsedMessage

-0.71

__*/

-0.67

MLLoader

-0.65

oredCriteria

-0.65

دانشنامهٔ

-0.65

Datuak

-0.61

ArrowToggle

-0.60

errHandler

-0.59

POSITIVE LOGITS

mathop

0.52

สุด

0.49

 Frie

0.48

kuper

0.48

restes

0.48

Цитата

0.47

 jLabel

0.47

lä

0.47

Erreferentziak

0.47



0.46

Activations Density 0.020%

syntax and structure related to Java classes and methods

Mathematical expressions and special characters

to replace

No Comments

No Known Activations