INDEX

Explanations

references to ownership and proprietorship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 μην

-0.77

 Ibis

-0.73

 Nora

-0.73

 wading

-0.71

Nora

-0.71

 Guth

-0.70

ellige

-0.69

 Vigo

-0.68

erà

-0.68

 Rats

-0.66

POSITIVE LOGITS

 owners

1.31

owners

1.22

 Owners

1.19

Owners

1.19

 OWNER

1.19

 owner

1.19

OWNER

1.16

 owned

1.11

owner

1.09

 ownership

1.08

Activations Density 0.055%

references to ownership and proprietorship

No Comments

No Known Activations