INDEX

Explanations

references to code, syntax, and technical inquiries related to programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+

-0.61

withIdentifier

-0.59

balleur

-0.54

ReusableCell

-0.53

 betweenstory

-0.52

хьтан

-0.51

 TimeSpan

-0.49

Tikang

-0.49

setVerticalGroup

-0.49

 الحره

-0.48

POSITIVE LOGITS

퀀

0.34

 pulseira

0.33

 barres

0.32

 contexte

0.31

 configuração

0.31

はじめに

0.30

 invokingState

0.30

Биография

0.30

 useParams

0.30

 характер

0.30

Activations Density 0.417%

references to code, syntax, and technical inquiries related to programming

No Comments

No Known Activations