INDEX

Explanations

phrases indicating statistical or analytical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Попис

-0.82

 imageNamed

-0.70

IBOutlet

-0.64

loh

-0.61

rungsseite

-0.61

bership

-0.60

 Gust

-0.59

IGENCE

-0.58

DrawerToggle

-0.57

Pautan

-0.57

POSITIVE LOGITS

+#+#

0.67

RenderAtEndOf

0.59

出版年

0.56

 küche

0.56

InvalidProtocol

0.55

MessageOf

0.52

]-->

0.51

 gereken

0.50

 frumo

0.48

 wohnung

0.48

Activations Density 0.151%

phrases indicating statistical or analytical references

No Comments

No Known Activations