INDEX

Explanations

instances of high-intensity emotional expressions or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Géographie

-0.50

 autorytatywna

-0.48

⎠

-0.46

 صوتيه

-0.46

GetBytes

-0.44

Gep

-0.44

 InputDecoration

-0.43

funny

-0.43

toPromise

-0.42

POSITIVE LOGITS

 nakalista

0.63

TagMode

0.59

0.51

 שוליים

0.46

 żyw

0.42

 propOrder

0.41

 Comprometido

0.40

exitRule

0.40

GEBURTS

0.40

ISODE

0.39

Activations Density 1.064%

instances of high-intensity emotional expressions or experiences

No Comments

No Known Activations