INDEX

Explanations

references to patents and related technical disclosures

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

Japanese patent publication numbers

np_acts-logits-general · gemini-2.0-flash

Kyutama characters

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

 dépend

-0.59

thâu

-0.59

ijnt

-0.54

 sumpay

-0.53

NgModule

-0.51

 ویکی‌پدیا

-0.51

 >=",

-0.51

GRANTED

-0.51

Sommer

-0.50

 Harwood

-0.50

POSITIVE LOGITS

脚注の使い方

0.69

 unknownFields

0.59

unknownFields

0.57

AndEndTag

0.56

 Besøkt

0.53

seis

0.51

ei

0.50

publicain

0.46

ho

0.46

 intptr

0.46

Activations Density 0.212%

references to patents and related technical disclosures

Japanese patent publication numbers

Kyutama characters

No Comments

No Known Activations