INDEX

Explanations

mathematical and logical expressions or statements

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

"is" followed by descriptive words

np_acts-logits-general · gemini-2.0-flash

is followed by a descriptor

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

 Potter

-0.48

abstra

-0.44

 Haven

-0.43

Tagged

-0.43

 wagen

-0.43

tpl

-0.42

 profiter

-0.42

curi

-0.41

姑

-0.41

 Telegram

-0.41

POSITIVE LOGITS

UnusedPrivate

0.96

 صوتيه

0.92

 OFDb

0.83

CloseOperation

0.74

CppMethod

0.68

 AssemblyVersion

0.67

Архівовано

0.67

MemoryWarning

0.66

Xna

0.65

Datuak

0.65

Activations Density 1.884%

mathematical and logical expressions or statements

"is" followed by descriptive words

is followed by a descriptor

No Comments

No Known Activations