INDEX

Explanations

specific modifications or changes within a technical context

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

Adding something new

np_acts-logits-general · gemini-2.0-flash

adding new things

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 élas

-0.62

MethodManager

-0.56

örm

-0.55

 BorderRadius

-0.54

 sauvages

-0.54

UnitTesting

-0.53

esModule

-0.53

 @"";

-0.53

شهاد

-0.51

enschaft

-0.50

POSITIVE LOGITS

 added

1.27

 addition

1.25

new

1.21

 additional

1.20

 adding

1.15

add

1.11

 additions

1.10

 추가

1.10

新增

1.07

新たに

1.06

Activations Density 0.521%

specific modifications or changes within a technical context

Adding something new

adding new things

No Comments

No Known Activations