INDEX

Explanations

structured data, particularly in regions and codes within a programming or data context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Followed by "region" or "Region"

np_acts-logits-general · gemini-2.0-flash

following region

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

AddHtmlAttribute

-0.55

EDEFAULT

-0.54

ArrowToggle

-0.52

hoeddwyd

-0.48

 iNdEx

-0.46

jooq

-0.45

__":

-0.44

cipar

-0.43

parsedMessage

-0.43

 समीक्षाएं

-0.42

POSITIVE LOGITS

 region

3.87

 Region

3.61

region

3.55

Region

3.41

 regions

3.31

 REGION

3.29

 regional

3.19

 Regions

3.02

regional

2.96

REGION

2.96

Activations Density 0.433%

structured data, particularly in regions and codes within a programming or data context

Followed by "region" or "Region"

following region

No Known Activations