INDEX

Explanations

concepts and terms related to mathematical properties and conditions in theoretical contexts

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

ending in "ity," "ness," or similar suffixes

np_acts-logits-general · gemini-2.0-flash

linearity assumption

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoScale

-0.67

LookAnd

-0.61

chengladbach

-0.60

RegistryLite

-0.59

beat

-0.53

ulemon

-0.53

salms

-0.51

ured

-0.51

ed

-0.49

 ffilmiau

-0.49

POSITIVE LOGITS

 assolu

0.70

 relativa

0.66

AddHtmlAttribute

0.64

 levels

0.64

 CreateTagHelper

0.64

iveau

0.62

 zelve

0.62

 beginnetje

0.60

issues

0.60

mybatisplus

0.59

Activations Density 0.630%

concepts and terms related to mathematical properties and conditions in theoretical contexts

ending in "ity," "ness," or similar suffixes

linearity assumption

No Comments

No Known Activations