INDEX

Explanations

expressions of preference or choices between options

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

 Audiodateien

-0.81

Gil

-0.69

Al

-0.67

</em>

-0.67

<h3>

-0.63

xDB

-0.63

 syscall

-0.63

zel

-0.62

Al

-0.62

 plot

-0.61

POSITIVE LOGITS

 préfé

1.42

 Prefer

1.38

 prefer

1.36

 preferred

1.33

 Preferred

1.33

prefer

1.31

 prefers

1.29

 preference

1.28

 Preferences

1.27

 Preference

1.26

Activations Density 0.076%

expressions of preference or choices between options

No Comments

No Known Activations