INDEX

Explanations

documents that contain only numerical or abstract representations without relevant textual content

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

Tokens after symbols or numbers

np_acts-logits-general · gemini-2.0-flash

technical, code snippets, or programming terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

featureID

-0.57

fø

-0.51

AsUp

-0.49

Personensuche

-0.49

 ویکی‌پدی

-0.48

verifyException

-0.45

 internacionais

-0.45

onChanged

-0.44

 perfetto

-0.44

 الوس

-0.43

POSITIVE LOGITS

extAlignment

0.76

ChildScrollView

0.70

etheless

0.68

CloseOperation

0.67

findpost

0.66

stdafx

0.66

Xna

0.65

 iParam

0.65

Portale

0.65

DockStyle

0.65

Activations Density 0.217%

documents that contain only numerical or abstract representations without relevant textual content

Tokens after symbols or numbers

technical, code snippets, or programming terms

No Comments

No Known Activations