INDEX

Explanations

instances of headings or structural markers in the text

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

Followed by letters or "without"

np_acts-logits-general · gemini-2.0-flash

mathematical expressions or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Abitanti

-0.81

Personensuche

-0.78

Geplaatst

-0.74

styleType

-0.73

 ―――――

-0.72

principalTable

-0.69

 cherchés

-0.69

verifyException

-0.69

ьаж

-0.69

SuppressLint

-0.68

POSITIVE LOGITS

Descripción

0.73

Abstract

0.57

Beschreibung

0.55

Beskrivelse

0.55

About

0.54

Description

0.52

Descrição

0.52

<strong>

0.49

Giới

0.48

چرا

0.46

Activations Density 0.099%

instances of headings or structural markers in the text

Followed by letters or "without"

mathematical expressions or descriptions

No Comments

No Known Activations