INDEX

Explanations

references to programming concepts or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 resourceCulture

-0.83

principalColumn

-0.83

IntoConstraints

-0.76

expandindo

-0.75

awtextra

-0.74

ReusableCell

-0.71

tagHelperRunner

-0.67

DeleteBehavior

-0.66

makeConstraints

-0.66

Identyfik

-0.65

POSITIVE LOGITS

 documentation

1.77

 docs

1.49

 Documentation

1.41

Documentation

1.39

documentation

1.37

doc

1.34

 documenta

1.26

 Docs

1.25

doc

1.24

Docs

1.21

Activations Density 1.350%

references to programming concepts or documentation

No Comments

No Known Activations