INDEX

Explanations

structures indicative of nested elements or data structures in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

pad

-0.30

 otra

-0.30

Inflater

-0.30

★★★

-0.29

floor

-0.28

mus

-0.27

对

-0.27

 another

-0.27

 alterations

-0.26

 rough

-0.25

POSITIVE LOGITS

+#+#

0.85

Diweddarwch

0.77

 initComponents

0.75

IntoConstraints

0.72

SharedCtor

0.72

 pinulongan

0.71

principalTable

0.71

parsedMessage

0.68

 дописавши

0.68

 createState

0.68

Activations Density 0.659%

structures indicative of nested elements or data structures in code

No Comments

No Known Activations