INDEX

Explanations

variables and mathematical expressions within formulas

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

mathematical notation and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

AndroidJUnit

-0.72

RectangleBorder

-0.64

OCCURRED

-0.63

 وتسجيلات

-0.60

 informée

-0.56

TypedDataSet

-0.54

-------------</

-0.54

AddHtmlAttribute

-0.51

AnchorTagHelper

-0.51

LookAnd

-0.50

POSITIVE LOGITS

исленность

0.37

byshev

0.36

adpleegd

0.33

iastes

0.32

اص

0.30

FunctionFlags

0.30

 Battista

0.30

 Governors

0.29

Governor

0.29

ayanan

0.29

Activations Density 0.030%

variables and mathematical expressions within formulas

mathematical notation and references

No Comments

No Known Activations