INDEX

Explanations

tokens associated with the beginning of a structured document or sections

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

Follows a capitalized word and period

np_acts-logits-general · gemini-2.0-flash

math or math-related expressions

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

 تضيفلها

-0.62

 consultato

-0.54

rungsseite

-0.54

 EnglishChoose

-0.54

tagHelperRunner

-0.54

aarrggbb

-0.54

FormTagHelper

-0.54

LookAnd

-0.53

Comté

-0.53

IntoConstraints

-0.53

POSITIVE LOGITS

Summary

0.68

 Summary

0.64

 Conclusion

0.63

enumii

0.62

getStringExtra

0.57

 {}));

0.55

 geleden

0.55

Overview

0.54

Conclusion

0.54

⏟

0.52

Activations Density 0.735%

tokens associated with the beginning of a structured document or sections

Follows a capitalized word and period

math or math-related expressions

No Comments

No Known Activations