INDEX

Explanations

references to academic papers or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

schul

-0.49

COGN

-0.46

po

-0.46

ætter

-0.44

 anything

-0.43

ծ

-0.43

wany

-0.43

 badly

-0.43

 evening

-0.43

 party

-0.42

POSITIVE LOGITS

########.

0.93

WebVitals

0.89

 kasarigan

0.85

PMailer

0.85

Билгалдахарш

0.84

 AppColors

0.83

↑

0.78

はじめに

0.75

Portail

0.75

/**

0.74

Activations Density 0.108%

references to academic papers or studies

No Comments

No Known Activations