INDEX

Explanations

terms related to legal definitions and processes, particularly in the context of crime and entrance

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

"entry" or "entering"

np_acts-logits-general · gemini-2.0-flash

entry or access to places

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Revi

-0.60

()]);

-0.59

IUrlHelper

-0.59

 JpaRepository

-0.58

 Waray

-0.57

úrate

-0.57

ніципалі

-0.56

styleable

-0.56

 Мексичка

-0.55

EndGlobalSection

-0.55

POSITIVE LOGITS

 entry

2.55

 entering

2.39

 entrance

2.38

 Entry

2.29

entry

2.20

 enters

2.20

 Entering

2.16

 entered

2.11

Entry

2.11

 ENTRY

2.10

Activations Density 0.376%

terms related to legal definitions and processes, particularly in the context of crime and entrance

"entry" or "entering"

entry or access to places

No Comments

No Known Activations