INDEX

Explanations

mathematical expressions and notations that represent complex relationships or calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 <=",

-0.64

 InputDecoration

-0.56

govina

-0.55

انيف

-0.53

IBOutlet

-0.53

اصيل

-0.52

 variant

-0.52

romp

-0.50

complexContent

-0.49

 onCreateView

-0.49

POSITIVE LOGITS

InjectAttribute

0.54

 behand

0.50

 weichen

0.50

 autorités

0.50

ellular

0.49

 poffible

0.49

 neceffary

0.49

 espirituales

0.48

 necessárias

0.48

 abstrato

0.47

Activations Density 0.521%

mathematical expressions and notations that represent complex relationships or calculations

No Comments

No Known Activations