INDEX

Explanations

instances of the word "complete."

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

 للاسماء

-0.70

titleMargin

-0.63

XmlEnum

-0.62

 Paglinawan

-0.60

XtraBars

-0.60

 fédé

-0.59

spyOn

-0.58

 vigueur

-0.57

 aflu

-0.57

 MATTERS

-0.56

POSITIVE LOGITS

 complete

4.91

complete

4.41

 Complete

4.33

Complete

4.21

 COMPLETE

3.96

COMPLETE

3.41

 completa

2.89

 completo

2.79

 complète

2.71

 komplet

2.47

Activations Density 0.112%

instances of the word "complete."

No Comments

No Known Activations