INDEX

Explanations

terms related to ownership and possession

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

ownership of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Haskell

-0.52

AddField

-0.52

hintText

-0.51

Hilsen

-0.50

Grüße

-0.50

PSI

-0.50

 Mardi

-0.50

 Fletcher

-0.50

 Garland

-0.50

 Delta

-0.49

POSITIVE LOGITS

 owned

1.04

 owns

0.96

 owning

0.95

 Owned

0.95

owned

0.94

 ownership

0.89

 Ownership

0.88

ownership

0.85

Owned

0.83

 owner

0.82

Activations Density 0.024%

terms related to ownership and possession

ownership of things

No Comments

No Known Activations