INDEX

Explanations

numeric data and statistical results related to voting and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Personendaten

-0.48

 crowning

-0.39

خبار

-0.38

⤹

-0.38

 Vorder

-0.37

 dimensión

-0.37

 Wunder

-0.37

Counter

-0.36

 premier

-0.36

vertical

-0.35

POSITIVE LOGITS

 initComponents

0.60

RegressionTest

0.56

 AssemblyCulture

0.51

ThroughAttribute

0.50

AccessorTable

0.48

__':

0.45

fortawesome

0.44

achella

0.44

codehaus

0.43

fjspx

0.43

Activations Density 0.414%

numeric data and statistical results related to voting and performance metrics

No Comments

No Known Activations