INDEX

Explanations

numerical values and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 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

ându

-0.54

 bờ

-0.52

 voluto

-0.52

atorul

-0.47

MLLoader

-0.47

 verheiratet

-0.46

Gambas

-0.46

före

-0.46

sodik

-0.45

parken

-0.45

POSITIVE LOGITS

reportWebVitals

0.49

gonic

0.46

esModule

0.44

setupUi

0.42

 propOrder

0.40

UnusedPrivate

0.39

parsedMessage

0.37

TargetException

0.35

–

0.35

wahati

0.34

Activations Density 0.779%

numerical values and statistics

No Comments

No Known Activations