INDEX

Explanations

references to objects and data structures in programming and analytical contexts

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

HttpDelete

-0.51

 kasarigan

-0.51

 zijne

-0.49

RegistryLite

-0.47

MLLoader

-0.47

 HomeController

-0.47

[++

-0.45

 Hälfte

-0.44

AddAttribute

-0.44

invokeLater

-0.44

POSITIVE LOGITS

principalColumn

0.42

wal

0.37

Lov

0.36

 existing

0.35

 parent

0.35

такт

0.35

 seeding

0.34

ärt

0.34

 foundations

0.34

 seed

0.34

Activations Density 1.360%

references to objects and data structures in programming and analytical contexts

No Comments

No Known Activations