INDEX

Explanations

references to errors and corrections in formal writing or documents

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

Mistakes, errors, and typos

np_acts-logits-general · gemini-2.0-flash

mistakes and errors

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

ArrowToggle

-0.52

ToBounds

-0.47

piram

-0.46

 BitmapFactory

-0.45

ValueGeneration

-0.45

aarrggbb

-0.44

ścioła

-0.44

 approach

-0.43

Pov

-0.42

GoogleApiClient

-0.42

POSITIVE LOGITS

 mistakenly

1.40

 incorrect

1.24

 mistake

1.22

 incorrectly

1.21

 mistaken

1.18

 wrong

1.18

 wrongly

1.15

incorrect

1.12

 erreur

1.11

 erroneously

1.11

Activations Density 0.381%

references to errors and corrections in formal writing or documents

Mistakes, errors, and typos

mistakes and errors

No Comments

No Known Activations