INDEX

Explanations

functions or commands related to updating data or user profiles

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

Updating or editing something

np_acts-logits-general · gemini-2.0-flash

update

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

enterOuterAlt

-0.48

 farewell

-0.47

LayoutStyle

-0.47

 OMIT

-0.46

 estr

-0.46

rola

-0.46

 Aussch

-0.45

 FileInputStream

-0.44

glGen

-0.43

(!__

-0.43

POSITIVE LOGITS

 update

2.32

 updating

2.22

update

2.08

 updated

2.08

 updates

2.03

 Update

2.02

 Updating

1.99

Update

1.96

 UPDATE

1.91

Updating

1.81

Activations Density 0.273%

functions or commands related to updating data or user profiles

Updating or editing something

update

No Comments

No Known Activations