INDEX

Explanations

form elements in HTML

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

before text fields or figures

np_acts-logits-general · gemini-2.0-flash

HTML attributes or proper names

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

 placent

-0.43

kursi

-0.42

si

-0.41

 Egli

-0.40

 solaire

-0.40

 głos

-0.39

 encore

-0.39

бей

-0.36

copus

-0.36

 ©️

-0.36

POSITIVE LOGITS

ंदीखरीदारी

0.85

 محفوظة

0.81

 MessageBoxIcon

0.79

0.77

ftagPool

0.75

 AssemblyTitle

0.75

 चीज़ों

0.75

addPreferredGap

0.73

 doInBackground

0.73

UserScript

0.72

Activations Density 0.086%

form elements in HTML

before text fields or figures

HTML attributes or proper names

No Comments

No Known Activations