INDEX

Explanations

statistical data related to health metrics and performance indicators

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

Comes before a number

np_acts-logits-general · gemini-2.0-flash

active registrations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

شن

-0.45

rój

-0.45

hun

-0.44

éndolo

-0.43

tzmann

-0.43

URIComponent

-0.42

ivo

-0.41

interopRequire

-0.40

imread

-0.40

CRY

-0.40

POSITIVE LOGITS

 active

0.98

active

0.90

 ACTIVE

0.85

Active

0.84

 Active

0.83

 registered

0.81

 aktiven

0.81

 actives

0.78

 aktive

0.78

 registrations

0.77

Activations Density 0.153%

statistical data related to health metrics and performance indicators

Comes before a number

active registrations

No Comments

No Known Activations