INDEX

Explanations

references to academic publications and their details

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

 AssemblyCulture

-0.91

 nahilalakip

-0.68

onViewCreated

-0.65

AsUp

-0.64

andaag

-0.63

AccessorTable

-0.62

-------------</

-0.60

kháu

-0.60

Biblia

-0.60

-0.58

POSITIVE LOGITS

 Aufl

0.52

AMES

0.50

ですから

0.48

tetur

0.48

AxisAlignment

0.48

 terbatas

0.47

 pity

0.47

人在

0.46

 profonde

0.45

ländischen

0.45

Activations Density 0.858%

references to academic publications and their details

No Comments

No Known Activations