INDEX

Explanations

structured data or code-like syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

葺

-0.51

دانشنامهٔ

-0.41

gner

-0.41

".

-0.40

<eos>

-0.40

 forme

-0.40

Tra

-0.40

 Gene

-0.39

帖最后由

-0.38

 ultimately

-0.38

POSITIVE LOGITS

 useRouter

0.77

 Inscrivez

0.73

 intermédiaire

0.70

 imageNamed

0.68

 Exacts

0.68

principalColumn

0.68

 Connectez

0.67

 Cæsar

0.67

 دیکھیے

0.67

neurial

0.67

Activations Density 0.318%

structured data or code-like syntax

No Comments

No Known Activations