INDEX

Explanations

mathematical or programming expressions, particularly those involving variables, operations, and functions

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

Code or mathematical expressions

np_acts-logits-general · gemini-2.0-flash

code, math, programming constructs

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

__);

-0.68

yes

-0.59

-0.56

Yes

-0.54

Yes

-0.53

 nein

-0.53

клопе

-0.53

 tỏi

-0.50

]$}

-0.49

 neutron

-0.49

POSITIVE LOGITS

 Baillargeon

0.61

stateProvider

0.59

 endforeach

0.57

)/

0.54

makeText

0.54

ArgsConstructor

0.54

 الرياضيه

0.53

wpi

0.52

 totalSupply

0.51

 GoogleFonts

0.50

Activations Density 0.984%

mathematical or programming expressions, particularly those involving variables, operations, and functions

Code or mathematical expressions

code, math, programming constructs

No Comments

No Known Activations