INDEX

Explanations

terms and classes related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 esternos

-0.65

ources

-0.63

srcs

-0.54

CloseOperation

-0.53

 sources

-0.53

からず

-0.52

verwijspagina

-0.52

 peaceful

-0.51

 autorytatywna

-0.51

 Sources

-0.50

POSITIVE LOGITS

 getItemId

0.59

 NSCoder

0.54

Gar

0.52

OrBuilder

0.52

readystatechange

0.51

gar

0.51

 Valentine

0.51

SourceChecksum

0.51

ništ

0.50

prepareStatement

0.50

Activations Density 2.624%

terms and classes related to programming and software development

No Comments

No Known Activations