INDEX

Explanations

expressions of appreciation or thanks

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

enumi

-0.66

enumii

-0.60

 تانيه

-0.57

 lack

-0.54

örm

-0.50

jer

-0.49

 стаття

-0.49

옵

-0.48

 وتسجيلات

-0.48

 União

-0.47

POSITIVE LOGITS

makeConstraints

0.71

($__

0.66

ArrowToggle

0.64

ViewFeatures

0.57

曖昧さ回避

0.56

uskas

0.56

 Họ

0.55

gbaar

0.54

 חיצוניים

0.54

Eksterne

0.53

Activations Density 0.017%

expressions of appreciation or thanks

No Comments

No Known Activations