INDEX

Explanations

mathematical notations and equivalences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ţiei

-0.55

cault

-0.53

(['/

-0.49

odymium

-0.49

erals

-0.49

uxley

-0.48

pry

-0.47

 längre

-0.47

்த்த

-0.46

oury

-0.46

POSITIVE LOGITS

addComponent

5.11

addGroup

1.33

 initComponents

1.29

awtextra

1.11

 MessageBoxIcon

1.05

ConstraintMaker

0.99

initComponents

0.97

IBOutlet

0.94

CloseOperation

0.92

 COMPONENT

0.89

Activations Density 0.009%

mathematical notations and equivalences

No Comments

No Known Activations