INDEX

Explanations

references to software extensions or packages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 initComponents

-0.49

 authorities

-0.41

 Nagel

-0.38

 typically

-0.38

typically

-0.38

 maintien

-0.37

 Misch

-0.37

 auquel

-0.37

 Heller

-0.37

 apunt

-0.36

POSITIVE LOGITS

extension

0.64

 extension

0.63

 Extension

0.58

Extension

0.56

 extensions

0.53

 EXTENSION

0.53

EXTENSION

0.51

 مشين

0.49

 Their

0.48

 endfor

0.48

Activations Density 0.061%

references to software extensions or packages

No Comments

No Known Activations