INDEX

Explanations

technical coding terms and elements related to software licenses and permissions

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

Code, licenses, and disclaimers

np_acts-logits-general · gemini-2.0-flash

implied warranty or license

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

sizeCache

-0.77

+#+#

-0.68

complexContent

-0.64

 unknownFields

-0.64

Jeografia

-0.64

CppMethod

-0.63

ValueGenerated

-0.62

QMetaType

-0.61

 Италијани

-0.61

POSITIVE LOGITS

GraphicsUnit

2.27

numerusform

0.58

 Kluwer

0.56

uxxxx

0.55

 equinox

0.54

Fordítás

0.54

point

0.53

Point

0.53

 Peninsula

0.53

 POINT

0.52

Activations Density 0.015%

technical coding terms and elements related to software licenses and permissions

Code, licenses, and disclaimers

implied warranty or license

No Comments

No Known Activations