INDEX

Explanations

HTML headings and formatting tags in the text

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

Follows HTML heading tags

np_acts-logits-general · gemini-2.0-flash

numbers or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 الرياضيه

-0.76

Atsauces

-0.72

ir

-0.71

Eksteraj

-0.71

ans

-0.70

du

-0.69

 AssemblyCulture

-0.69

 تضيفلها

-0.68

ípio

-0.68

Šalt

-0.68

POSITIVE LOGITS

<h2>

1.07

 itſelf

1.03

 juſt

0.99

 deſt

0.95

 Sarm

0.94

 leſs

0.93

 nemici

0.92

 greateſt

0.91

 fevere

0.90

 Româ

0.90

Activations Density 0.053%

HTML headings and formatting tags in the text

Follows HTML heading tags

numbers or titles

No Comments

No Known Activations