INDEX

Explanations

numbers and numeric sequences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ifferentiated

-0.62

 DRAWINGS

-0.58

("")]

-0.54

ticello

-0.51

hysema

-0.50

uscular

-0.48

 vanden

-0.48

prefixer

-0.47

kegaard

-0.47

 hither

-0.47

POSITIVE LOGITS

abestanden

0.83

 الحره

0.82

 AssemblyCompany

0.76

</caption>

0.63

providedIn

0.61

contentLoaded

0.61

/*

0.58

 متعلقه

0.58

astify

0.58

 aigu

0.58

Activations Density 0.296%

numbers and numeric sequences

No Comments

No Known Activations