INDEX

Explanations

syntactic structures such as nested braces or parentheses in programming-like syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 java

-0.46

 going

-0.45

Msk

-0.44

 offers

-0.44

 <<<<<<<<<<<<<<

-0.43

こともあります

-0.42

 this

-0.42

ことができました

-0.42

gène

-0.42

piv

-0.41

POSITIVE LOGITS

 épis

0.71

 consommateurs

0.70

 acrylique

0.70

 ujednoznacz

0.70

 médicale

0.69

 chré

0.69

 NgModule

0.69

reportWebVitals

0.68

Искәрмәләр

0.68

 تانيه

0.68

Activations Density 1.191%

syntactic structures such as nested braces or parentheses in programming-like syntax

No Comments

No Known Activations