INDEX

Explanations

technical or programming terms related to configuration and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 CreateTagHelper

-0.52

 defaultstate

-0.52

 صوتيه

-0.49

EndInit

-0.46

AndEndTag

-0.44

postsleuth

-0.43

 فريبيس

-0.43

 disambiguazione

-0.42

 مرئيه

-0.40

 linkovi

-0.40

POSITIVE LOGITS

 Normdatei

0.47

enderror

0.46

这个时候

0.44

 exploding

0.43

/**

0.42

 overpowered

0.42

esan

0.42

arot

0.42

URLException

0.41

 tricked

0.41

Activations Density 4.808%

technical or programming terms related to configuration and settings

No Comments

No Known Activations