INDEX

Explanations

references to processes and transactions in computing contexts

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

SequentialGroup

-0.34

$_['

-0.32

-------------</

-0.31

бливості

-0.31

PreferredItem

-0.30

edge

-0.29

Scénario

-0.29

fine

-0.28

monary

-0.28

POSITIVE LOGITS

 customers

0.57

 invokingState

0.57

customers

0.52

 Customers

0.51

 Biôgrafia

0.50

 GreatSchools

0.50

 purchasers

0.50

TagMode

0.49

Customers

0.48

 pelanggan

0.48

Activations Density 0.053%

references to processes and transactions in computing contexts

No Comments

No Known Activations