INDEX

Explanations

references to locking mechanisms and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 varandra

-0.89

 rendus

-0.85

 réaliste

-0.83

 therefrom

-0.83

twimg

-0.82

 flesta

-0.82

 profonde

-0.82

windigkeit

-0.81

 circonst

-0.81

 suivante

-0.81

POSITIVE LOGITS

 lock

1.55

 LOCK

1.50

 Lock

1.48

 locks

1.48

 Locks

1.45

Locks

1.45

lock

1.31

locks

1.30

LOCK

1.29

 locked

1.26

Activations Density 0.071%

references to locking mechanisms and related concepts

No Comments

No Known Activations