INDEX

Explanations

symbols and delimiters used in mathematical or programming contexts

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

Aligned mathematical expressions

np_acts-logits-general · gemini-2.0-flash

LaTeX formatting and equation labels

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

UnknownFieldSet

-0.58

◄

-0.56

المناصب

-0.55

LabelTagHelper

-0.54

webElementXpaths

-0.52

RegressionTest

-0.51

Ranks

-0.49

 longue

-0.49

 defaultstate

-0.49

NullCheck

-0.48

POSITIVE LOGITS

center

0.63

 uintptr

0.58

 tartalomajánló

0.56

Ārējās

0.55

InteropServices

0.54

 estimés

0.54

utilisons

0.53

 voetballer

0.53

 Reverso

0.52

UserScript

0.51

Activations Density 0.029%

symbols and delimiters used in mathematical or programming contexts

Aligned mathematical expressions

LaTeX formatting and equation labels

No Comments

No Known Activations