INDEX

Explanations

terms related to licenses and permits

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

permissions or authorization

np_acts-logits-general · gemini-2.0-flash

licenses and visas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Sorg

-0.53

GroupLayout

-0.52

УДК

-0.49

鞠

-0.49

ird

-0.48

 surla

-0.48

зулта

-0.45

чатый

-0.44

amazonaws

-0.44

done

-0.43

POSITIVE LOGITS

 granted

1.23

 holders

1.17

 renewal

1.13

 holder

1.11

 revoked

1.07

 expire

1.07

 renewals

1.06

 issued

1.04

 expiring

1.03

 Holders

1.01

Activations Density 0.391%

terms related to licenses and permits

permissions or authorization

licenses and visas

No Comments

No Known Activations