INDEX

Explanations

phrases indicating importance or significance in context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

#+#

-0.68

RectangleBorder

-0.56

httphttps

-0.55

RegressionTest

-0.53

EDEFAULT

-0.51

canestro

-0.50

ConstraintMaker

-0.50

PerformLayout

-0.48

APOLIS

-0.47

GOTREF

-0.47

POSITIVE LOGITS

Externé

0.44

Citiți

0.43

 виправивши

0.40

 Bewußt

0.38

PrivateRoute

0.36

 cuar

0.35

 kasarigan

0.35

 vuestros

0.35

$_[

0.35

 مشين

0.34

Activations Density 0.836%

phrases indicating importance or significance in context

No Comments

No Known Activations