INDEX

Explanations

technical terms and references to software components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

anglès

-0.50

ToolStripButton

-0.49

://

-0.48

parsedMessage

-0.47

 also

-0.46

 Master

-0.46

 Biôgrafia

-0.45

 Black

-0.44

 Google

-0.42

ToListAsync

-0.42

POSITIVE LOGITS

脚注の使い方

0.74

følgelig

0.71

 محفوظة

0.69

 endforeach

0.69

 commonwealth

0.69

sedown

0.67

 Syrians

0.66

engertian

0.66

])));

0.65

 perfume

0.62

Activations Density 2.177%

technical terms and references to software components

No Comments

No Known Activations