INDEX

Explanations

terms related to quantum mechanics and particle interactions, specifically involving electrons and their behavior in different states

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

เภ

-0.62

:✨

-0.60

 Meksiku

-0.60

hending

-0.57

 verz

-0.56

 richi

-0.56

rande

-0.55

žas

-0.54

 INVENTION

-0.54

gdx

-0.53

POSITIVE LOGITS

 electrons

1.37

ctrons

1.08

 electron

1.08

electrons

1.07

electron

1.07

proton

1.04

 proton

1.03

 Electron

1.01

Proton

0.97

 Proton

0.93

Activations Density 0.524%

terms related to quantum mechanics and particle interactions, specifically involving electrons and their behavior in different states

No Comments

No Known Activations