INDEX

Explanations

phrases that involve questions and comparisons about identity and differences

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

 teş

-0.54

ACD

-0.49

cu

-0.49

 fournir

-0.49

 élevées

-0.49

-0.48

Bissau

-0.47

はや

-0.47

énom

-0.47

supply

-0.47

POSITIVE LOGITS

 कैसे

0.94

+:+

0.92

how

0.91

יצד

0.90

 如何

0.88

 怎样

0.88

 initComponents

0.88

 Nasıl

0.86

 nahilalakip

0.85

 Himo

0.83

Activations Density 0.126%

phrases that involve questions and comparisons about identity and differences

No Comments

No Known Activations