INDEX

Explanations

expressions of personal preference or choice

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Audiodateien

-0.76

Al

-0.73

Gil

-0.68

Tom

-0.65

</em>

-0.65

 syscall

-0.64

brecht

-0.63

liters

-0.63

<h3>

-0.63

xDB

-0.62

POSITIVE LOGITS

 préfé

1.33

 Prefer

1.33

 Preferred

1.27

prefer

1.26

 Preference

1.25

 Preferences

1.24

 prefer

1.24

 preferred

1.23

 preference

1.22

 prefers

1.18

Activations Density 0.054%

expressions of personal preference or choice

No Comments

No Known Activations