INDEX

Explanations

references to challenges and awards in educational or interactive settings

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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



-0.50

 kasarigan

-0.45

łoś

-0.42

 voeten

-0.40

beitung

-0.40

 getItemId

-0.38

 Italijanski

-0.37

#+#

-0.37

WebpackPlugin

-0.37

 صوتيه

-0.37

POSITIVE LOGITS

 campaign

0.44

 success

0.43

setColumns

0.42

íslu

0.42

 caus

0.41

MLLoader

0.40

 Kolle

0.40

setupUi

0.40

 incentiv

0.39

corre

0.39

Activations Density 0.011%

references to challenges and awards in educational or interactive settings

No Comments

No Known Activations