INDEX

Explanations

mathematical symbols and operations related to sums, limits, and indices

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

Mathematical or special characters

np_acts-logits-general · gemini-2.0-flash

mathematical notation and superscripts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

鼎

-0.36

Britannique

-0.31

cum

-0.31

 conj

-0.31

|()

-0.31

ナツ

-0.30

 bent

-0.30

言

-0.29

bul

-0.29

 bare

-0.29

POSITIVE LOGITS

 surla

0.69

 Autorizaciones

0.64

<sup>

0.58

aarrggbb

0.57

 arşivlendi

0.57

ंदीखरीदारी

0.56

 виправивши

0.54

${

0.53

 iParam

0.52

Personensuche

0.52

Activations Density 1.720%

mathematical symbols and operations related to sums, limits, and indices

Mathematical or special characters

mathematical notation and superscripts

No Comments

No Known Activations