INDEX

Explanations

references to notes or annotations in the text

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

The token "Note" and its variations

np_acts-logits-general · gemini-2.0-flash

introduces explanatory notes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 DriverManager

-0.60

ிரு

-0.54

nasel

-0.51

ității

-0.51

handleClick

-0.50

álního

-0.50

 couv

-0.50

ALITY

-0.50

чатый

-0.49

POSITIVE LOGITS

 notes

1.26

 Notes

1.23

Notes

1.08

 note

1.08

 NOTE

1.02

 NOTES

1.02

 Note

0.99

notes

0.97

 Nota

0.91

Note

0.90

Activations Density 0.085%

references to notes or annotations in the text

The token "Note" and its variations

introduces explanatory notes

No Comments

No Known Activations