INDEX

Explanations

terms related to scientific research and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

<bos>

-0.50

thâu

-0.44

Personensuche

-0.44

bak

-0.43

bc

-0.42

+:+

-0.42

bac

-0.42

jsii

-0.41

 biss

-0.41

 тогда

-0.41

POSITIVE LOGITS

 recent

0.81

 recently

0.79

 reciente

0.79

Recently

0.73

 recentemente

0.71

 recientemente

0.71

 récente

0.71

recently

0.70

 recente

0.70

 kürzlich

0.69

Activations Density 0.210%

terms related to scientific research and analysis

No Comments

No Known Activations