INDEX

Explanations

specific geographic locations or administrative divisions

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

or abbreviations followed by a period

np_acts-logits-general · gemini-2.0-flash

names and abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

DataAnnotations

-0.47

basicConfig

-0.47

JAKARTA

-0.46

 ultimate

-0.45

 Arlington

-0.45

 Williams

-0.45

printStackTrace

-0.45

Dunn

-0.44

 Dunn

-0.44

 UnityEditor

-0.44

POSITIVE LOGITS

oso

0.63

og

0.62

oto

0.61

oz

0.59

od

0.59

odo

0.58

oyo

0.58

oid

0.58

ode

0.58

oy

0.58

Activations Density 1.670%

specific geographic locations or administrative divisions

or abbreviations followed by a period

names and abbreviations

No Comments

No Known Activations