INDEX

Explanations

letters and alphanumeric sequences, particularly in technical or formal contexts

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

rungsseite

-0.54

Sådan

-0.52

 limão

-0.51

ținut

-0.49

Viungo

-0.48

 persoons

-0.48

 între

-0.47

Personensuche

-0.47

 almendras

-0.47

 vrijwilli

-0.47

POSITIVE LOGITS

useNewUrlParser

0.38

ThemeOverlay

0.38

 houſe

0.37

0.36

]")]

0.36

 AssemblyProduct

0.36

0.35

 Sikh

0.35

Yii

0.34

Activations Density 0.376%

letters and alphanumeric sequences, particularly in technical or formal contexts

No Comments

No Known Activations