INDEX

Explanations

terms and phrases related to visual representations and illustrations

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

Japanese and Russian text

np_acts-logits-general · gemini-2.0-flash

Japanese colloquial endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

jsxFileName

-0.70

 لينك

-0.52

ANTLR

-0.51

 automatiques

-0.49

 publiques

-0.47

 IMPLIED

-0.47

workbook

-0.47

 vectoriales

-0.47

prefixer

-0.46

 alimentaires

-0.46

POSITIVE LOGITS

Organisateur

0.60

je

0.54

ising

0.54

eting

0.54

izing

0.53

isation

0.52

LabelTagHelper

0.52

йте

0.51

 ExecuteAsync

0.50

ably

0.50

Activations Density 0.076%

terms and phrases related to visual representations and illustrations

Japanese and Russian text

Japanese colloquial endings

No Comments

No Known Activations